© 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. 44775
    Prev
    Next
    INDEX
    Explanations

    Islamic

    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
     pulses
    -0.09
     Diva
    -0.08
    回事
    -0.08
    ptious
    -0.08
    、安全
    -0.08
     pelas
    -0.08
    安全吗
    -0.07
     dàng
    -0.07
     стру
    -0.07
    elta
    -0.07
    POSITIVE LOGITS
     कृषि
    0.09
     ':'
    0.08
     Agricultural
    0.08
    iyi
    0.08
    -covered
    0.08
    -operated
    0.08
     colon
    0.08
    .environment
    0.08
     opér
    0.08
     '=',
    0.08
    Activations Density 0.002%

    No Known Activations