© 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. 11-RESID-POST-AA
    11. 26513
    Prev
    Next
    INDEX
    Explanations

    Units of distance/speed

    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
     red
    -0.09
    red
    -0.09
     ше
    -0.08
     шах
    -0.08
    Red
    -0.07
    urika
    -0.07
    ERING
    -0.07
     Red
    -0.07
     You
    -0.07
    ered
    -0.07
    POSITIVE LOGITS
     yn
    0.09
     naon
    0.08
     inconvenience
    0.08
     housekeeping
    0.08
     fractions
    0.08
     rn
    0.08
     domést
    0.08
    ouches
    0.08
     ringan
    0.08
     കുറ്റ
    0.07
    Activations Density 0.027%

    No Known Activations