© 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. 19-RESID-POST-AA
    11. 103513
    Prev
    Next
    INDEX
    Explanations

    payment processors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Authentication
    -0.09
     身
    -0.09
     Shopping
    -0.08
    สินค้า
    -0.08
    .shopping
    -0.08
     selfies
    -0.08
     ऐप
    -0.08
     Shopper
    -0.08
     Wallet
    -0.08
    注文
    -0.08
    POSITIVE LOGITS
     processors
    0.12
     processor
    0.12
    Processor
    0.11
     Processor
    0.11
     verwerking
    0.11
    _processor
    0.11
    processor
    0.11
     агрег
    0.10
    _processors
    0.10
     gateways
    0.10
    Activations Density 0.007%

    No Known Activations