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. 23-RESID-POST-AA
    6. 98171
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plum
    -0.07
    RES
    -0.07
     reo
    -0.07
     VAT
    -0.07
     Resolution
    -0.07
     CAT
    -0.07
     bundles
    -0.07
     SOURCE
    -0.07
    water
    -0.07
     ric
    -0.07
    POSITIVE LOGITS
    স্প
    0.10
    ા
    0.09
    ুষ
    0.08
    íns
    0.08
    াগত
    0.08
    া
    0.08
    ínsula
    0.08
    ıcı
    0.07
    ximity
    0.07
     Уч
    0.07
    Activations Density 0.000%

    No Known Activations