arxiv
PublishedJune 17, 2026 at 4:00 AM
—neutral
Stable and Steerable Sparse Autoencoders with Weight Regularization
Publisher summary· verbatim
arXiv:2603.04198v2 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) are widely used to extract human-interpretable features from neural network activations, but their learned features can vary substantially across random seeds and training choices. To improve stability, we studied w
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivAlignment Plausibility: A New Standard for Assuring AI in Healthcare6harxivIdiobionics: The Unification of Privacy and Intelligent Robotic Prostheses6harxivVectorizationLLM: Smart Vectorization Based AI Assistant6harxivA Graph Neural Network Model for Real-Time Gesture Recognition Based on sEMG Signals6hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗