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. 112087
    Prev
    Next
    INDEX
    Explanations

    `

    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
     Cruiser
    -0.09
     Natural
    -0.08
    azes
    -0.08
     ndo
    -0.08
     stripper
    -0.08
     Cate
    -0.08
     osim
    -0.08
     طبیعی
    -0.08
     naturelle
    -0.08
     diva
    -0.08
    POSITIVE LOGITS
    )
    0.08
     whereas
    0.08
    ));↵
    0.07
    .where
    0.07
    (where
    0.07
    "/>.↵
    0.07
    .resolve
    0.07
    (
    0.07
     deduct
    0.07
     عام
    0.07
    Activations Density 0.034%

    No Known Activations