© 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. 91204
    Prev
    Next
    INDEX
    Explanations

    code, data, programming

    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
    iphery
    -0.08
    Slope
    -0.08
    -switch
    -0.07
     resumen
    -0.07
    jective
    -0.07
     heading
    -0.07
     snapping
    -0.07
     Recipro
    -0.07
     iniciado
    -0.07
    <Edge
    -0.07
    POSITIVE LOGITS
     bik
    0.09
     ಸಂಪ
    0.08
     läb
    0.08
    DBG
    0.08
    ہوں
    0.08
    сти
    0.07
    完整
    0.07
    риш
    0.07
     dolgo
    0.07
    бря
    0.07
    Activations Density 0.000%

    No Known Activations