© 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. 23-RESID-POST-AA
    11. 50286
    Prev
    Next
    INDEX
    Explanations

    ед

    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
     occas
    -0.09
    cação
    -0.07
     السف
    -0.07
     stabile
    -0.07
     kwan
    -0.07
     appealed
    -0.07
     letan
    -0.07
    lana
    -0.07
     আস
    -0.07
     taum
    -0.07
    POSITIVE LOGITS
    вед
    0.10
    onged
    0.08
    vě
    0.07
    enj
    0.07
    वी
    0.07
    不是
    0.07
    ING
    0.07
    oused
    0.07
     TED
    0.07
    jó
    0.07
    Activations Density 0.000%

    No Known Activations