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. 111889
    Prev
    Next
    INDEX
    Explanations

    code or density

    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
     olie
    -0.09
    afima
    -0.08
    雄
    -0.08
     Decisions
    -0.08
    pressive
    -0.08
     oil
    -0.07
    odin
    -0.07
     Olim
    -0.07
    _MAIN
    -0.07
     तेल
    -0.07
    POSITIVE LOGITS
     enve
    0.07
    ,Integer
    0.07
    Kansas
    0.07
    Marco
    0.07
     USPS
    0.07
    }|
    0.07
    Warp
    0.07
     Las
    0.07
     marché
    0.07
     Parlament
    0.07
    Activations Density 0.000%

    No Known Activations