Author

Haoyang Luo

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Jul 2026

Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations

This work introduces Persistent Sparse Autoencoders (Persistent SAEs), an extension of standard SAEs that learns a persistence coefficient for each feature, allowing the model to learn feature-specific timescales from reconstruction alone.

Haoyang Luo, M. Zarlenga, M. Jamnik · 0 citations