© 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. 19-RESID-POST-AA
    11. 102586
    Prev
    Next
    INDEX
    Explanations

    boolean logic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -format
    -0.08
    Tree
    -0.08
    Win
    -0.08
    _WIN
    -0.08
    uci
    -0.07
    Certain
    -0.07
     کنید
    -0.07
    ைத்து
    -0.07
    /List
    -0.07
    SQL
    -0.07
    POSITIVE LOGITS
     reversed
    0.16
     opposite
    0.15
     differences
    0.14
     diferença
    0.14
     differing
    0.14
     flipped
    0.13
     oppos
    0.13
     diferenças
    0.13
     identical
    0.13
     oposição
    0.13
    Activations Density 0.020%

    No Known Activations