© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45387
    Prev
    Next
    INDEX
    Explanations

    React code

    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
    落实
    -0.08
    (cursor
    -0.08
     kete
    -0.07
     miss
    -0.07
     actually
    -0.07
    壇
    -0.07
     দেয়া
    -0.07
     dadas
    -0.07
    &i
    -0.07
     మీద
    -0.07
    POSITIVE LOGITS
     voorzichtig
    0.08
     caution
    0.08
     vors
    0.08
     yapı
    0.07
     disposizione
    0.07
     rozp
    0.07
    Gob
    0.07
     gro
    0.07
     των
    0.07
    Month
    0.07
    Activations Density 0.001%

    No Known Activations