© 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. 19-RESID-POST-AA
    11. 102350
    Prev
    Next
    INDEX
    Explanations

    load

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kses
    -0.09
     Kristu
    -0.09
    ాత్ర
    -0.08
     wak
    -0.08
    ณ์
    -0.08
     BLACK
    -0.07
    -së
    -0.07
    BLACK
    -0.07
     kusho
    -0.07
     njeng
    -0.07
    POSITIVE LOGITS
    ings
    0.13
    Unload
    0.10
    unately
    0.10
    -bearing
    0.09
    ­ing
    0.09
    илась
    0.09
     المزيد
    0.09
    ively
    0.09
    ummed
    0.09
    ers
    0.09
    Activations Density 0.014%

    No Known Activations