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. 88105
    Prev
    Next
    INDEX
    Explanations

    image analysis and measurement

    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
    aryawan
    -0.08
    aked
    -0.08
    IONAL
    -0.08
    updates
    -0.08
     Revel
    -0.08
    Updates
    -0.08
    케팅
    -0.08
     hemp
    -0.08
     предусмотр
    -0.08
     Updates
    -0.08
    POSITIVE LOGITS
    .extract
    0.14
     extracting
    0.14
     extraction
    0.13
    _extract
    0.13
    extract
    0.12
     استخراج
    0.12
     widths
    0.12
    Extraction
    0.11
     extracted
    0.11
     Extract
    0.11
    Activations Density 0.017%

    No Known Activations