© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31263
    Prev
    Next
    INDEX
    Explanations

    puzzles and riddles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LNG
    -0.10
     lubrication
    -0.09
    тенсив
    -0.09
     AMG
    -0.09
    柴油
    -0.09
     androgen
    -0.08
    _dma
    -0.08
    _DMA
    -0.08
     instrumentation
    -0.08
     Whiskey
    -0.08
    POSITIVE LOGITS
     puzzles
    0.24
    谜
    0.22
    Puzzle
    0.20
     puzzle
    0.19
     Puzzle
    0.18
     Sudoku
    0.17
    -solving
    0.16
     crossword
    0.16
     sudoku
    0.15
     puzz
    0.15
    Activations Density 0.059%

    No Known Activations