© 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. 47215
    Prev
    Next
    INDEX
    Explanations

    glue

    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
     trivia
    -0.08
    Trivia
    -0.08
     Torre
    -0.08
    維
    -0.08
     tunes
    -0.08
     accesses
    -0.08
    Å
    -0.08
    .DES
    -0.07
    /XMLSchema
    -0.07
    _https
    -0.07
    POSITIVE LOGITS
    _MARGIN
    0.08
     xiri
    0.08
     विवाह
    0.08
     bapt
    0.07
    ivil
    0.07
     Bapt
    0.07
     chur
    0.07
     WARRANT
    0.07
     boter
    0.07
     Margin
    0.07
    Activations Density 0.011%

    No Known Activations