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. 30619
    Prev
    Next
    INDEX
    Explanations

    display

    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
    遂
    -0.08
     ṣiṣe
    -0.07
     Ebene
    -0.07
    打造
    -0.07
    oude
    -0.07
     vile
    -0.07
     تتم
    -0.07
     Reihe
    -0.07
     Temple
    -0.07
    仔
    -0.07
    POSITIVE LOGITS
     uninter
    0.08
    ите
    0.08
    出来
    0.08
     disclaim
    0.08
     результатов
    0.08
     unchanged
    0.08
    .error
    0.08
    ผล
    0.08
     misleading
    0.08
     Isn
    0.07
    Activations Density 0.041%

    No Known Activations