Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 19228
    Prev
    Next
    INDEX
    Explanations

    What

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    crito
    -0.10
    cula
    -0.09
     সীম
    -0.09
     quels
    -0.09
    ánchez
    -0.09
    ahoo
    -0.09
     cantidades
    -0.09
    culo
    -0.09
     limitar
    -0.09
    vidos
    -0.09
    POSITIVE LOGITS
    .↵↵
    0.09
     we
    0.08
     there
    0.08
     matters
    0.08
     executed
    0.08
    ?↵↵
    0.08
     should
    0.08
     all
    0.08
     you
    0.08
     is
    0.08
    Activations Density 0.008%

    No Known Activations