© 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. 99243
    Prev
    Next
    INDEX
    Explanations

    distance

    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
     lively
    -0.08
     situated
    -0.08
     Situated
    -0.07
    Scope
    -0.07
     Mustang
    -0.07
     gracious
    -0.07
     ભૂ
    -0.07
    uyan
    -0.07
     Islamic
    -0.07
    anlagen
    -0.07
    POSITIVE LOGITS
     traveled
    0.09
     violet
    0.08
    不到
    0.08
     tới
    0.08
    是多少
    0.08
     đến
    0.08
    รวม
    0.08
    들을
    0.08
     travelled
    0.08
     fu
    0.08
    Activations Density 0.037%

    No Known Activations