© 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. 26106
    Prev
    Next
    INDEX
    Explanations

    vere

    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
    ‌آ
    -0.08
     resolutions
    -0.08
    —but
    -0.07
    ̌
    -0.07
     মাহ
    -0.07
     maps
    -0.07
    ontal
    -0.07
    weh
    -0.07
     Maps
    -0.07
    ._↵
    -0.06
    POSITIVE LOGITS
    етка
    0.09
    Zeros
    0.08
    来了
    0.07
    rokken
    0.07
     vole
    0.07
    едия
    0.07
    转载请
    0.07
    中过
    0.07
    期
    0.07
    Ability
    0.07
    Activations Density 0.001%

    No Known Activations