© 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. 108685
    Prev
    Next
    INDEX
    Explanations

    π

    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
     Crescent
    -0.10
     Kre
    -0.09
     çek
    -0.09
    ക്ട
    -0.08
     Antibi
    -0.08
     pa
    -0.08
     antibiotic
    -0.08
     Pa
    -0.08
     holl
    -0.08
     Simpson
    -0.08
    POSITIVE LOGITS
     radians
    0.07
    <const
    0.07
     embark
    0.07
    embr
    0.07
     <>
    0.07
    પ્ર
    0.07
    jaz
    0.07
    OTA
    0.07
     symbolize
    0.07
    unstyled
    0.07
    Activations Density 0.007%

    No Known Activations