© 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. 68173
    Prev
    Next
    INDEX
    Explanations

    our

    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
     ponerse
    -0.08
     către
    -0.08
    bindung
    -0.07
     강화
    -0.07
     convertirse
    -0.07
     ना
    -0.07
     mantenerse
    -0.07
    awed
    -0.07
     आदि
    -0.07
     altında
    -0.07
    POSITIVE LOGITS
    題
    0.08
     છીએ
    0.08
    smarty
    0.07
    毛
    0.07
    题
    0.07
     munt
    0.07
    šem
    0.07
     Staats
    0.07
     можем
    0.07
     Dumb
    0.07
    Activations Density 0.014%

    No Known Activations