© 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. 15-RESID-POST-AA
    11. 16661
    Prev
    Next
    INDEX
    Explanations

    Dis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     પછી
    -0.09
     gekeken
    -0.09
     mellett
    -0.09
     vwar
    -0.09
     prochaine
    -0.09
     бәр
    -0.09
     وروسته
    -0.09
     meesha
    -0.09
     રાહ
    -0.09
     nkarhi
    -0.09
    POSITIVE LOGITS
     Languages
    0.08
    "，
    0.08
     Different
    0.08
    百科
    0.07
    _language
    0.07
     languages
    0.07
     Definitions
    0.07
     Settings
    0.07
     Related
    0.07
    "
    0.07
    Activations Density 0.009%

    No Known Activations