Unverified50% confidenceFactExact time
TopK SAE is a class of autoencoders that learn sparse features by forcing the hidden-layer activations of each token to retain at most k non-zero values, unlike traditional SAEs that use L1 regularization to encourage sparsity.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDeno.Kv's tuple key encoding uses type tags plus 20-digit zero-padded numbers (n:, b:, s:), separated by null bytes, so that SQLite range queries can match Deno KV's sort order.52% similarVerifiedRRF is a tuning-free rank fusion algorithm that uses only rank positions, accumulating scores as 1/(k+rank), with the constant k typically set to 60.51% similarUnverifiedThe anchor divergence method operates on fixed representations and obtains similarity metrics oriented toward different semantic requirements by specifying different anchor distributions, without retraining the encoder.50% similarUnverifiedThe Top-K pruning strategy is essentially a branch-and-bound algorithm based on a priority queue (min-heap).50% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1129399API
curl https://kongchang.com/api/v1/knowledge/claims/1129399MCP
get_claim(id=1129399)