© 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. 45451
    Prev
    Next
    INDEX
    Explanations

    mains

    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
    yny
    -0.08
    izy
    -0.08
     كأس
    -0.07
     cob
    -0.07
    coli
    -0.07
     Conrad
    -0.07
    ardige
    -0.07
    昭
    -0.07
    Fernando
    -0.07
     насколько
    -0.07
    POSITIVE LOGITS
     dictionaries
    0.08
     incontourn
    0.08
     usw
    0.08
     Specials
    0.08
    jeun
    0.08
     geplant
    0.07
     __(
    0.07
     -------↵
    0.07
    (:,:,
    0.07
     überlegen
    0.07
    Activations Density 0.011%

    No Known Activations