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. 58466
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     가지
    -0.08
     linda
    -0.08
     engineered
    -0.08
    工程
    -0.08
     organisator
    -0.07
     Hockey
    -0.07
     상담
    -0.07
    ’re
    -0.07
    routine
    -0.07
     engineers
    -0.07
    POSITIVE LOGITS
     czyli
    0.08
     (=
    0.08
     अर्थात
    0.08
     అంటే
    0.08
     यानी
    0.08
     એટલે
    0.08
     дзе
    0.08
     apo
    0.07
     clientele
    0.07
     म्हणजे
    0.07
    Activations Density 0.004%

    No Known Activations