© 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. 3062
    Prev
    Next
    INDEX
    Explanations

    rounding

    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
     TOT
    -0.08
    Ontology
    -0.07
     `<
    -0.07
     elder
    -0.07
     Torres
    -0.07
     Accept
    -0.07
     Bee
    -0.07
     autant
    -0.07
     Kuh
    -0.07
     indicate
    -0.07
    POSITIVE LOGITS
     ді
    0.08
     verm
    0.08
     cori
    0.08
    丁
    0.08
     مص
    0.07
    gil
    0.07
    .Pattern
    0.07
     Bend
    0.07
    िज
    0.07
    乔
    0.07
    Activations Density 0.014%

    No Known Activations