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. 55938
    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
     fashioned
    -0.09
    utim
    -0.08
    ############################################################################
    -0.08
     Counsel
    -0.08
    -0.08
    า
    -0.08
     thoughtfully
    -0.08
     Cole
    -0.08
     presa
    -0.08
     vuole
    -0.07
    POSITIVE LOGITS
     ಒ
    0.08
    bairro
    0.07
     ચૂક
    0.07
     ಹೆಚ್ಚ
    0.07
    ogen
    0.07
    ondas
    0.07
     finalist
    0.07
    .csv
    0.07
     rumah
    0.07
    (ref
    0.07
    Activations Density 0.001%

    No Known Activations