© 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. 45381
    Prev
    Next
    INDEX
    Explanations

    picture

    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
     Tipp
    -0.09
    費
    -0.08
    tong
    -0.08
     Wissen
    -0.07
     Springfield
    -0.07
    🏼
    -0.07
     spelled
    -0.07
    TD
    -0.07
     cavern
    -0.07
     bowel
    -0.07
    POSITIVE LOGITS
     Joe
    0.08
    -perfect
    0.07
    ğraf
    0.07
     HE
    0.07
    angles
    0.07
    0.07
    截图
    0.07
    /jpeg
    0.07
    Joe
    0.07
     Dell
    0.07
    Activations Density 0.018%
    No Known Activations