TopK sparse autoencoders trained at matched sparsity and dictionary size on Llama-3.2-3B, Mistral-7B-v0.3 and Qwen2.5-3B. Reports abrupt dictionary collapse followed by partial recovery, dense-feature degeneracy severe enough to invalidate frequency-based feature selection, and a null cross-architecture matching result whose detection floor is measured directly by planted-signal power analysis at correlation 0.95 to 1.00.