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. 12121
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    /linux
    -0.08
    _music
    -0.08
    ("?
    -0.08
    NORMAL
    -0.08
     alluring
    -0.08
    /bin
    -0.08
     brochures
    -0.07
     Allison
    -0.07
     struggling
    -0.07
    (before
    -0.07
    POSITIVE LOGITS
    沿
    0.09
     elementos
    0.09
     central
    0.09
     aggrav
    0.09
     централь
    0.09
     connecting
    0.09
    元素
    0.08
     съд
    0.08
     элементы
    0.08
     travers
    0.08
    Activations Density 0.015%

    No Known Activations