© 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. 11-RESID-POST-AA
    11. 44611
    Prev
    Next
    INDEX
    Explanations

    cron jobs

    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
    pics
    -0.08
     topar
    -0.08
     streaming
    -0.07
     Cumhur
    -0.07
     abort
    -0.07
     sell
    -0.07
    sell
    -0.07
    sales
    -0.07
    abort
    -0.07
    GDP
    -0.07
    POSITIVE LOGITS
    criture
    0.10
    永久
    0.10
     screws
    0.09
     dacht
    0.09
    ábh
    0.09
    Permanent
    0.09
    כשיו
    0.09
     כתב
    0.09
     Schrift
    0.09
     ჩან
    0.08
    Activations Density 0.004%

    No Known Activations