© 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. 11-RESID-POST-AA
    11. 112424
    Prev
    Next
    INDEX
    Explanations

    9

    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
    ROID
    -0.07
     serius
    -0.07
     Sé
    -0.07
     ök
    -0.07
    żej
    -0.07
     traditionnel
    -0.07
     father's
    -0.07
    荒
    -0.07
    oute
    -0.07
     Nevertheless
    -0.07
    POSITIVE LOGITS
     baking
    0.10
     ресторан
    0.09
    浅
    0.09
    atanga
    0.09
     bakery
    0.08
    Pizza
    0.08
     restaurant
    0.08
     muffins
    0.08
    pizza
    0.08
    -inch
    0.08
    Activations Density 0.006%

    No Known Activations