© 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. 45231
    Prev
    Next
    INDEX
    Explanations

    real

    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
     kugira
    -0.08
     comrades
    -0.08
    เพื่อ
    -0.08
    毒
    -0.08
     politischen
    -0.08
    .Commit
    -0.08
     Commit
    -0.07
     मस
    -0.07
    -I
    -0.07
    цов
    -0.07
    POSITIVE LOGITS
    整数
    0.09
     shaved
    0.08
    求
    0.08
     dividend
    0.08
     exponent
    0.08
     tame
    0.07
    iple
    0.07
     receives
    0.07
    unsigned
    0.07
     expon
    0.07
    Activations Density 0.010%

    No Known Activations