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. 53792
    Prev
    Next
    INDEX
    Explanations

    data

    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
     Gladi
    -0.08
    elong
    -0.08
     contestant
    -0.08
     protr
    -0.08
     elong
    -0.08
    ELLOW
    -0.08
     slit
    -0.08
    <HTML
    -0.08
     Nob
    -0.07
     velvet
    -0.07
    POSITIVE LOGITS
     sources
    0.10
    /api
    0.09
    .entities
    0.09
    來源
    0.09
    .datasource
    0.09
     datasource
    0.09
    .repositories
    0.09
    /providers
    0.08
    .kt
    0.08
    paging
    0.08
    Activations Density 0.002%

    No Known Activations