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. 77459
    Prev
    Next
    INDEX
    Explanations

    part

    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
     תש
    -0.08
     retire
    -0.07
     umr
    -0.07
    /compiler
    -0.07
     مرحله
    -0.07
     hoor
    -0.07
    voit
    -0.07
    уре
    -0.07
    ине
    -0.07
     compiler
    -0.07
    POSITIVE LOGITS
     לימ
    0.09
     시작
    0.08
     Contrary
    0.08
    -horizontal
    0.08
    लों
    0.08
    _horizontal
    0.08
     verticale
    0.08
     Starting
    0.08
     फोन
    0.08
    .Start
    0.08
    Activations Density 0.002%

    No Known Activations