© 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. 24729
    Prev
    Next
    INDEX
    Explanations

    --

    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
    有
    -0.08
     inte
    -0.07
     настолько
    -0.07
    事
    -0.07
    valu
    -0.07
     emper
    -0.07
     hush
    -0.07
    だった
    -0.07
     things
    -0.07
    Mond
    -0.07
    POSITIVE LOGITS
     Satur
    0.08
    igare
    0.08
     sɛ
    0.08
     Prob
    0.08
     .↵↵↵
    0.08
    ígeno
    0.08
     flange
    0.07
     modo
    0.07
     guise
    0.07
    DMA
    0.07
    Activations Density 0.010%

    No Known Activations