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. 15-RESID-POST-AA
    6. 19300
    Prev
    Next
    INDEX
    Explanations

    right angles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bulshada
    -0.08
     mbalimbali
    -0.08
    -0.08
     interessant
    -0.08
    Kwam
    -0.08
     moeite
    -0.08
     samo
    -0.08
    �读
    -0.07
     murah
    -0.07
     regularly
    -0.07
    POSITIVE LOGITS
     nibh
    0.08
    .',
    0.08
    .↵↵
    0.08
     prise
    0.08
    ',↵
    0.08
     nanti
    0.08
     remaining
    0.07
    uster
    0.07
    /r
    0.07
    .',↵
    0.07
    Activations Density 0.009%

    No Known Activations