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. 44072
    Prev
    Next
    INDEX
    Explanations

    frac

    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
    beck
    -0.08
    �
    -0.08
    /url
    -0.08
     partid
    -0.08
     убед
    -0.07
    _rgctx
    -0.07
    бира
    -0.07
     lids
    -0.07
    Retro
    -0.07
    kaj
    -0.07
    POSITIVE LOGITS
     tube
    0.08
    ziplin
    0.08
     virtual
    0.08
    バ
    0.07
    虚
    0.07
     readable
    0.07
     Mannheim
    0.07
     accom
    0.07
    cemia
    0.07
     voit
    0.07
    Activations Density 0.011%

    No Known Activations