© 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. 78489
    Prev
    Next
    INDEX
    Explanations

    trigonometry

    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
     tiền
    -0.08
     experimental
    -0.07
     norske
    -0.07
     visiting
    -0.07
    _TEMP
    -0.07
     mingi
    -0.07
     বে�
    -0.07
     sift
    -0.07
     nuggets
    -0.07
     squirrels
    -0.07
    POSITIVE LOGITS
     Stap
    0.08
    Ort
    0.08
    ────
    0.08
    zc
    0.08
     निर्�
    0.08
     feugiat
    0.07
    Cy
    0.07
     Vá
    0.07
    #w
    0.07
    otechn
    0.07
    Activations Density 0.002%

    No Known Activations