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. 11797
    Prev
    Next
    INDEX
    Explanations

    multiplication

    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
        ↵    ↵
    -0.08
    గ్య
    -0.08
     servant
    -0.08
    ಸು
    -0.08
     schlechten
    -0.08
    clients
    -0.08
    олага
    -0.08
    ilares
    -0.08
     slechte
    -0.07
     poor
    -0.07
    POSITIVE LOGITS
    ike
    0.08
    alem
    0.08
     Ao
    0.08
    abcdefghijkl
    0.07
     Kesk
    0.07
     ke
    0.07
    uffix
    0.07
     whai
    0.07
    ls
    0.07
     vle
    0.07
    Activations Density 0.032%

    No Known Activations