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. 112147
    Prev
    Next
    INDEX
    Explanations

    welding

    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
    .days
    -0.09
    .times
    -0.09
     страницы
    -0.09
    .pages
    -0.09
     страниц
    -0.08
     сен
    -0.08
     lujo
    -0.08
     luck
    -0.08
     ystä
    -0.08
    .Widget
    -0.08
    POSITIVE LOGITS
     welding
    0.12
     weld
    0.11
     alloy
    0.10
     свар
    0.10
     Welding
    0.10
     alloys
    0.09
     nozzle
    0.09
     carbur
    0.09
     solder
    0.08
     carbide
    0.08
    Activations Density 0.010%

    No Known Activations