© 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. 26119
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     값을
    -0.08
    字段
    -0.08
     Barrel
    -0.08
     aren
    -0.07
     forbindelse
    -0.07
     상태
    -0.07
     Infos
    -0.07
     hind
    -0.07
     ise
    -0.07
     unchanged
    -0.07
    POSITIVE LOGITS
     narrated
    0.08
     গবেষ
    0.08
     মহান
    0.08
    beautiful
    0.08
     روایت
    0.08
    antos
    0.08
     siapa
    0.08
    Kevin
    0.08
    研究
    0.08
    relig
    0.07
    Activations Density 0.121%

    No Known Activations