© 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. 108170
    Prev
    Next
    INDEX
    Explanations

    of

    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
    身
    -0.08
     pratique
    -0.08
     Ech
    -0.08
     filmed
    -0.08
    袭
    -0.08
     Botox
    -0.08
    偷拍
    -0.08
     المج
    -0.08
     hunted
    -0.07
    цен
    -0.07
    POSITIVE LOGITS
     бухгалтер
    0.11
     ledger
    0.10
    账
    0.09
     ngân
    0.09
     payable
    0.09
     счета
    0.09
    Invoice
    0.09
    Assign
    0.09
     financieros
    0.09
    余额
    0.09
    Activations Density 0.007%

    No Known Activations