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. 111847
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    កម្ម
    -0.08
    cube
    -0.08
    ियो
    -0.08
    ეშე
    -0.08
    _sheet
    -0.08
    .Mode
    -0.08
     mú
    -0.07
     Babel
    -0.07
    ಿಯೋ
    -0.07
    .book
    -0.07
    POSITIVE LOGITS
     život
    0.08
    (timestamp
    0.07
     preguntas
    0.07
     Findings
    0.07
     screenings
    0.07
     screening
    0.07
     গ্র
    0.07
     overige
    0.07
    _range
    0.07
     diagn
    0.07
    Activations Density 0.015%

    No Known Activations