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. 60847
    Prev
    Next
    INDEX
    Explanations

    mascots

    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
     zak
    -0.08
     nny
    -0.08
    所谓
    -0.08
     ər
    -0.07
     şekilde
    -0.07
    housing
    -0.07
    ijzig
    -0.07
     huizen
    -0.07
    திர
    -0.07
     الا
    -0.07
    POSITIVE LOGITS
     হিসাবে
    0.08
     adjunct
    0.08
    apult
    0.08
     হিসেবে
    0.08
    /logo
    0.08
     mascot
    0.08
     Wooden
    0.07
     lion
    0.07
     名
    0.07
     exagger
    0.07
    Activations Density 0.002%

    No Known Activations