arXiv AI June 11, 2026 By Gleb Gerasimov, Timofei Rusalev, Nikita Balagansky, Daniil Laptev, Vadim Kurochkin, Daniil Gavrilov

Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders

Read the original on arXiv AI →

arXiv:2606. 12138v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are widely used to interpret neural network representations, but their utility depends on whether the learned features are reproducible across training runs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 18

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability

arXiv:2606. 18383v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable features from language models (LMs), yet a central question remains: when can an SAE-based explanation be treated as a faithful view of an underlying frozen LM We study this through a post-hoc generalization framework that certifies the LM via a sparse proxy, obtained by replacing a native hidden activation with its pretrained SAE reconstruction.

By Dibyanayan Bandyopadhyay, Asif Ekbal

llms efficiency safety

arXiv Machine Learning

Aug 10

Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data

arXiv:2511. 09432v2 Announce Type: replace Abstract: Machine learning (ML) models achieve remarkable performance but remain hard to interpret due to their scale and complexity.

By Ege Erdogan, Ana Lucic

safety

arXiv Machine Learning

Aug 18

MoRFI: Monotonic Sparse Autoencoder Feature Identification

arXiv:2604. 26866v2 Announce Type: replace-cross Abstract: Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction.

By Dimitris Dimakopoulos, Shay B. Cohen, Ioannis Konstas

llms fine-tuning safety

arXiv AI

Jun 16

Rational Sparse Autoencoder

arXiv:2606. 14990v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are standard tools for mechanistic interpretability, but current SAE families are constrained by fixed encoder nonlinearities such as ReLU, JumpReLU, and TopK.

By Naiyu Yin, Yue Yu

llms fine-tuning efficiency safety

arXiv AI

Jul 15

Sparse Autoencoders for Interpretable Out-of-Distribution Detection

arXiv:2607. 12094v1 Announce Type: cross Abstract: Reliable detection of out-of-distribution (OOD) samples is crucial for the safe deployment of machine learning models.

By Ayush Karmacharya (Purdue University), Luke Luschwitz (Purdue University), Lucia Romero (Purdue University), Yanan Niu (EPFL), Joseph Campbell (Purdue University)

benchmarks

arXiv AI

Jul 28

Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects

arXiv:2607. 24645v1 Announce Type: cross Abstract: The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between SAE features and model behavior.

By Phu Gia Hoang, Anwoy Chatterjee, Tanmoy Chakraborty, Iryna Gurevych, Subhabrata Dutta

safety

One email a morning, machine-written

Related stories

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability

Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data

MoRFI: Monotonic Sparse Autoencoder Feature Identification

Rational Sparse Autoencoder

Sparse Autoencoders for Interpretable Out-of-Distribution Detection

Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects