© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1039
    Prev
    Next
    INDEX
    Explanations

    Japanese character 気

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kind
    -0.09
     periód
    -0.07
    Exports
    -0.07
     phil
    -0.07
     export
    -0.07
     ep
    -0.07
    .au
    -0.07
     Export
    -0.07
    Georgia
    -0.07
     perte
    -0.07
    POSITIVE LOGITS
    ää
    0.08
     bf
    0.08
     �
    0.07
     Km
    0.07
     burners
    0.07
     kawa
    0.07
     ನಿಧ
    0.07
     Lancaster
    0.07
     inference
    0.07
    Km
    0.07
    Activations Density 0.001%

    No Known Activations