© 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. 47775
    Prev
    Next
    INDEX
    Explanations

    smart

    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
     स्थल
    -0.08
    ীদ
    -0.08
    ीय
    -0.08
    иск
    -0.08
     Fever
    -0.07
     baptism
    -0.07
    黄
    -0.07
    /window
    -0.07
     históricos
    -0.07
     pax
    -0.07
    POSITIVE LOGITS
    fully
    0.09
    聪
    0.09
     smarter
    0.09
     워
    0.08
    -faire
    0.08
    ไป
    0.08
    elligent
    0.08
    licer
    0.07
     Köp
    0.07
    フォン
    0.07
    Activations Density 0.037%

    No Known Activations