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. 43760
    Prev
    Next
    INDEX
    Explanations

    scam emails

    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
    (template
    -0.08
     template
    -0.08
    ाठी
    -0.08
    ളുടെ
    -0.08
    Template
    -0.08
     player's
    -0.07
    Click
    -0.07
    Expand
    -0.07
    apan
    -0.07
    Morning
    -0.07
    POSITIVE LOGITS
     Markle
    0.09
     лучше
    0.09
     echter
    0.08
    indic
    0.08
     NONINFRINGEMENT
    0.08
     أفضل
    0.08
    േരിക്ക
    0.08
     будь
    0.08
     хоть
    0.08
     najle
    0.08
    Activations Density 0.011%

    No Known Activations