© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 69971
    Prev
    Next
    INDEX
    Explanations

    Currency subunits

    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
     welcoming
    -0.09
     நிகழ
    -0.08
     projecting
    -0.08
     gimnasio
    -0.08
     litr
    -0.08
    <IEnumerable
    -0.08
    encils
    -0.08
    Listado
    -0.08
    genes
    -0.08
     γεγον
    -0.07
    POSITIVE LOGITS
    人民币
    0.12
    金额
    0.11
     denominations
    0.10
    金币
    0.10
     division
    0.10
     cryptocurrencies
    0.10
     refundable
    0.10
    零钱
    0.10
     refunded
    0.10
     divisions
    0.09
    Activations Density 0.014%

    No Known Activations