© 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. 47161
    Prev
    Next
    INDEX
    Explanations

    multilingual

    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
    парат
    -0.08
    人体
    -0.08
     Централь
    -0.08
     Fy
    -0.08
     aapp
    -0.08
    ーパ
    -0.08
     смер
    -0.07
    Phy
    -0.07
     Тор
    -0.07
     Florence
    -0.07
    POSITIVE LOGITS
     sarcas
    0.08
     procrast
    0.08
    迟
    0.08
    /test
    0.08
     profiss
    0.08
    ，我
    0.07
     comprehend
    0.07
    昨天
    0.07
     persu
    0.07
     dogod
    0.07
    Activations Density 0.034%

    No Known Activations