© 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. 11-RESID-POST-AA
    11. 64611
    Prev
    Next
    INDEX
    Explanations

    in

    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
    անական
    -0.09
    ிக்க
    -0.08
    、安全
    -0.08
     гай
    -0.08
    ameda
    -0.08
    anker
    -0.08
    弊
    -0.08
     веса
    -0.08
    ிக்கை
    -0.08
    ိဳ
    -0.08
    POSITIVE LOGITS
    _caption
    0.08
     Mog
    0.08
    Style
    0.07
     Style
    0.07
    .env
    0.07
     illustrations
    0.07
    خ
    0.07
     cartoons
    0.07
    nh
    0.07
     Animal
    0.07
    Activations Density 0.003%

    No Known Activations