© 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. 54389
    Prev
    Next
    INDEX
    Explanations

    living

    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
    yük
    -0.08
     analogous
    -0.08
    碍
    -0.08
    Diagn
    -0.07
    きを
    -0.07
    ipped
    -0.07
    出了
    -0.07
    貨
    -0.07
    ferencia
    -0.07
     correlations
    -0.07
    POSITIVE LOGITS
    .gui
    0.08
    GUILayout
    0.08
     regulatory
    0.07
     gérer
    0.07
     seems
    0.07
     природ
    0.07
     IMPORT
    0.07
     naturels
    0.07
     eyebrows
    0.07
     {↵↵/
    0.07
    Activations Density 0.004%

    No Known Activations