© 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. 23-RESID-POST-AA
    11. 50358
    Prev
    Next
    INDEX
    Explanations

    Armistice/Phone numbers/Years

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saia
    -0.09
    ående
    -0.09
     ofer
    -0.08
     põhj
    -0.08
     screams
    -0.08
     Autónoma
    -0.08
    шую
    -0.08
     Pequ
    -0.08
     παί
    -0.08
     бед
    -0.08
    POSITIVE LOGITS
    MP
    0.09
    Drive
    0.08
    FLASH
    0.07
    mp
    0.07
    Injector
    0.07
     MP
    0.07
     ಮೀ
    0.07
     mp
    0.07
    drive
    0.07
    .v
    0.07
    Activations Density 0.003%

    No Known Activations