Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90171
    Prev
    Next
    INDEX
    Explanations

    the

    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
     обратно
    -0.08
    ادت
    -0.08
     erhielt
    -0.08
     enemmän
    -0.08
     exciting
    -0.07
    PRIVATE
    -0.07
     PRIVATE
    -0.07
     кан
    -0.07
     Hace
    -0.07
    ++;
    -0.07
    POSITIVE LOGITS
    Doctrine
    0.11
     teachings
    0.10
     Doctrine
    0.10
     Guidance
    0.10
     doctrine
    0.09
     Welfare
    0.09
     welfare
    0.09
     stewardship
    0.08
     doctrines
    0.08
    ั่ง
    0.08
    Activations Density 0.043%

    No Known Activations