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. 44150
    Prev
    Next
    INDEX
    Explanations

    glove box

    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
     singers
    -0.08
     vocal
    -0.08
    ದ
    -0.08
     vocals
    -0.08
     wake
    -0.08
     goodbye
    -0.08
     groceries
    -0.08
     آواز
    -0.08
     मतदान
    -0.08
    down
    -0.08
    POSITIVE LOGITS
     কাল
    0.08
     spe
    0.08
     Nc
    0.07
    empor
    0.07
     intrac
    0.07
     Spe
    0.07
    šu
    0.07
    exe
    0.07
     timelines
    0.07
    udal
    0.07
    Activations Density 0.019%

    No Known Activations