© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1363
    Prev
    Next
    INDEX
    Explanations

    Down syndrome

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ossz
    -0.08
    keepers
    -0.08
    पट
    -0.08
     differently
    -0.08
     kalt
    -0.08
    固
    -0.07
     deuda
    -0.07
     grime
    -0.07
    flamm
    -0.07
    362
    -0.07
    POSITIVE LOGITS
     silver
    0.08
     methyl
    0.08
     élet
    0.07
     GH
    0.07
    yee
    0.07
     balloon
    0.07
    杨
    0.07
     Wid
    0.07
    worksheet
    0.07
     balloons
    0.07
    Activations Density 0.003%

    No Known Activations