© 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. 11-RESID-POST-AA
    11. 70977
    Prev
    Next
    INDEX
    Explanations

    ceramic

    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
     hectic
    -0.08
     NDA
    -0.08
     учет
    -0.08
     Concord
    -0.08
     Discord
    -0.07
     Headquarters
    -0.07
     headquarters
    -0.07
     medidas
    -0.07
     concord
    -0.07
     jitter
    -0.07
    POSITIVE LOGITS
     pottery
    0.14
     ceramic
    0.13
     ceramics
    0.13
    陶
    0.10
     Ceramic
    0.10
     kiln
    0.09
     glaze
    0.09
     baking
    0.09
     изделий
    0.09
     enamel
    0.09
    Activations Density 0.022%

    No Known Activations