Optimal preservation of entangled features under whitened linear erasure
Determine whether optimally whitened linear operators can achieve quantitatively improved preservation of feature A while erasing feature B at intermediate entanglement, compared with the unwhitened rank-1 projection studied in the Toy Model of Superposition.
References
At intermediate $\rho$ (Table~\ref{tab:linear_baseline}), the degradation is specific to our unwhitened rank-1 projection; optimally whitened linear operators might yield quantitatively different preservation curves, which we leave to future work.
— Hidden not Deleted: How Networks Suppress Entangled Features
(2609.27593 - Samanta et al., 23 Sep 2026) in Section 3.3, subsection “Linear erasure fails”