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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 47299
    Prev
    Next
    INDEX
    Explanations

    Raw/Down

    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
     humo
    -0.08
     mord
    -0.08
     rad
    -0.08
     �
    -0.07
     высокого
    -0.07
     RAD
    -0.07
     lượng
    -0.07
     неж
    -0.07
    BAC
    -0.07
     evidente
    -0.07
    POSITIVE LOGITS
     sessions
    0.09
     semanal
    0.08
     Sundays
    0.08
    Instruction
    0.08
     diariamente
    0.08
     luar
    0.08
    ariant
    0.07
     postar
    0.07
    (session
    0.07
    ("?
    0.07
    Activations Density 0.003%

    No Known Activations