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. 76424
    Prev
    Next
    INDEX
    Explanations

    Proper nouns/abbreviations

    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
     (↵↵
    -0.08
    652
    -0.08
    empel
    -0.08
    uel
    -0.07
    fordern
    -0.07
     SAC
    -0.07
     кол
    -0.07
     populair
    -0.07
     dangerously
    -0.07
    ayat
    -0.07
    POSITIVE LOGITS
     Trong
    0.08
    Viewer
    0.08
     Ol
    0.08
     kës
    0.07
    工作的
    0.07
    Anh
    0.07
     Hà
    0.07
     outlook
    0.07
     έτσι
    0.07
    Fetcher
    0.07
    Activations Density 0.287%

    No Known Activations