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. 53155
    Prev
    Next
    INDEX
    Explanations

    text

    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
    nee
    -0.07
    entie
    -0.07
    otch
    -0.07
    clazz
    -0.07
     호
    -0.07
    passen
    -0.07
    ன்ன
    -0.07
    loopt
    -0.07
     dirige
    -0.07
    elee
    -0.07
    POSITIVE LOGITS
     [+
    0.08
     ▲
    0.08
    (Path
    0.08
    SECONDS
    0.07
     alph
    0.07
    (GET
    0.07
     forc
    0.07
     NG
    0.07
     Bog
    0.07
     Brother
    0.07
    Activations Density 0.001%

    No Known Activations