© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25056
    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
     Knock
    -0.07
     Manc
    -0.07
     Fass
    -0.07
     Abbas
    -0.07
     Mercado
    -0.07
    ,N
    -0.07
    长期
    -0.07
    िभ
    -0.07
     الشع
    -0.07
     الحقيقة
    -0.07
    POSITIVE LOGITS
     cents
    0.09
     ஒன்று
    0.08
    entañ
    0.08
     celebrating
    0.08
    ritable
    0.08
     daquele
    0.08
     quero
    0.08
     ਇਕ
    0.08
     ours
    0.08
    _DECL
    0.08
    Activations Density 0.015%

    No Known Activations