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. 98525
    Prev
    Next
    INDEX
    Explanations

    �

    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
    ろん
    -0.08
    ட்
    -0.08
     agreed
    -0.08
    シ
    -0.08
    ುದು
    -0.07
    ろ
    -0.07
    יינו
    -0.07
     gepl
    -0.07
    ਠ
    -0.07
     soddis
    -0.07
    POSITIVE LOGITS
    �
    0.11
    ile
    0.10
     Plugin
    0.09
    _plugin
    0.08
     Styles
    0.08
     filme
    0.08
    plugins
    0.08
     koho
    0.08
     Plugins
    0.08
    ilean
    0.08
    Activations Density 0.000%

    No Known Activations