AbsTopK Improves Sparse Autoencoders for Bidirectional Features
AbsTopK, a sparse autoencoder that keeps both positive and negative activations, lets one unit capture opposite concepts. Posted on arXiv (2510.00404) Oct 2025. Read more: getnews.me/abstopk-improves-sparse-... #abstopk #sparseautoencoders
0
0
0
0