© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 43004
    Prev
    Next
    INDEX
    Explanations

    overnight

    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
    อล
    -0.08
    HW
    -0.08
    vollen
    -0.08
    keä
    -0.07
     vint
    -0.07
     afflicted
    -0.07
    ẹrẹ
    -0.07
     dicht
    -0.07
    voll
    -0.07
    otores
    -0.07
    POSITIVE LOGITS
     overnight
    0.09
    -night
    0.08
     osm
    0.08
    /night
    0.08
    Bom
    0.08
    以来
    0.08
     improvements
    0.08
    ýn
    0.07
    _daily
    0.07
     المج
    0.07
    Activations Density 0.003%

    No Known Activations