© 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. 47252
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    fiber
    -0.08
    yst
    -0.07
     mantra
    -0.07
     ਫ
    -0.07
    ysta
    -0.07
    -f
    -0.07
    clipse
    -0.07
    qt
    -0.07
     wrinkles
    -0.07
    rr
    -0.07
    POSITIVE LOGITS
     hardly
    0.08
     mitä
    0.08
     lick
    0.08
     claramente
    0.08
     제외
    0.08
     veuillez
    0.08
     seres
    0.08
    هغه
    0.08
     sanitary
    0.08
     hes
    0.08
    Activations Density 0.007%

    No Known Activations