© 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 EvalsExportsinterp-engineNEWAPI 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. 110773
    Prev
    Next
    INDEX
    Explanations

    Nullable

    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
     להג
    -0.08
    -It
    -0.08
     vex
    -0.08
     ultime
    -0.08
     imperson
    -0.08
     în
    -0.08
     pinnacle
    -0.08
     ताकि
    -0.08
     inim
    -0.08
     lind
    -0.08
    POSITIVE LOGITS
    Nullable
    0.08
    Overwrite
    0.07
     overloaded
    0.07
    Overrides
    0.07
     مطلب
    0.07
     нормы
    0.07
    ó
    0.07
    [t
    0.07
    unuz
    0.07
     Jes
    0.07
    Activations Density 0.001%

    No Known Activations