© 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. 78288
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas/functions and code

    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
    است
    -0.09
    кту
    -0.08
     سای
    -0.08
    完成
    -0.08
    _FIN
    -0.08
    ésitez
    -0.07
    提交
    -0.07
     Stanton
    -0.07
     окончания
    -0.07
     ####
    -0.07
    POSITIVE LOGITS
     bo
    0.09
     buc
    0.08
    (with
    0.08
     bubbling
    0.08
     bubbly
    0.08
     pum
    0.07
     JK
    0.07
     ery
    0.07
     തന്നെ
    0.07
     boosters
    0.07
    Activations Density 0.012%

    No Known Activations