© 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. 45288
    Prev
    Next
    INDEX
    Explanations

    rolling eyes

    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
    หลาย
    -0.10
    Bush
    -0.08
    ප
    -0.08
    不中
    -0.08
    Strategies
    -0.08
     Bush
    -0.08
    Paths
    -0.07
    หล
    -0.07
    Stop
    -0.07
    _STOP
    -0.07
    POSITIVE LOGITS
     faa
    0.09
     nemo
    0.09
     grin
    0.08
     divertida
    0.08
     встав
    0.08
     Fur
    0.08
     verme
    0.08
     glamour
    0.08
     fa
    0.08
     reply
    0.08
    Activations Density 0.002%

    No Known Activations