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. 53046
    Prev
    Next
    INDEX
    Explanations

    with

    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
     pika
    -0.08
    兴
    -0.08
     относится
    -0.08
     statue
    -0.08
     جهاز
    -0.08
    ارض
    -0.08
     Une
    -0.08
     Speech
    -0.08
     fala
    -0.07
     titik
    -0.07
    POSITIVE LOGITS
    .xlsx
    0.17
     spreadsheet
    0.17
     spreadsheets
    0.17
    _excel
    0.16
    Excel
    0.15
    .xls
    0.15
    Worksheet
    0.14
    Spreadsheet
    0.14
     VBA
    0.14
     worksheets
    0.14
    Activations Density 0.025%

    No Known Activations