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. 11752
    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
    Git
    -0.08
    Crypt
    -0.08
    Isa
    -0.08
    Ge
    -0.08
    Gradu
    -0.07
     Christopher
    -0.07
     tavoitte
    -0.07
    Taxi
    -0.07
     nero
    -0.07
    DIY
    -0.07
    POSITIVE LOGITS
    ингов
    0.09
    arnas
    0.09
     слав
    0.08
     moindre
    0.08
     bang
    0.08
     coupling
    0.08
    merkt
    0.08
    lebihan
    0.08
    лам
    0.08
     Asians
    0.07
    Activations Density 0.000%

    No Known Activations