Author

Nandita N. Patil

h-index 0 View on Semantic Scholar

We have 1 of 2 papers

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.

Preprint Sep 2026

PhysSAE: Mechanistic Interpretability of PINNs with Sparse Autoencoders

PhysSAE, a mechanistic interpretability framework that trains overcomplete sparse autoencoders (SAEs) on PINN penultimate-layer activations and evaluates dictionary atoms through direct causal intervention in the original frozen hidden state, is presented.

Nandita N. Patil, A. EshwarR, G. Honnavar · 0 citations