© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103482
    Prev
    Next
    INDEX
    Explanations

    BBC

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ћу
    -0.08
    ću
    -0.08
    (e
    -0.08
    @Table
    -0.08
    /function
    -0.08
    ‼
    -0.08
    (expression
    -0.08
    lap
    -0.07
     ($
    -0.07
    /$
    -0.07
    POSITIVE LOGITS
     News
    0.12
     Mundo
    0.11
     نيوز
    0.10
    iplayer
    0.10
     Afaan
    0.10
     新闻
    0.10
     Hausa
    0.10
     Sport
    0.10
     Inggris
    0.09
     Zwei
    0.09
    Activations Density 0.003%

    No Known Activations