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. 53030
    Prev
    Next
    INDEX
    Explanations

    Gatherings and events

    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
    53
    -0.08
    .expr
    -0.07
     fourth
    -0.07
     ক্ষেত্রে
    -0.07
    .types
    -0.07
    qy
    -0.07
    /environment
    -0.07
     receptors
    -0.07
     unor
    -0.07
    ungu
    -0.07
    POSITIVE LOGITS
     annually
    0.09
     annuel
    0.09
     आयोजित
    0.09
     anual
    0.08
    メント
    0.08
     desayuno
    0.08
     ежегод
    0.08
    ”活动
    0.08
     অনুষ্ঠিত
    0.08
     camar
    0.08
    Activations Density 0.065%

    No Known Activations