© 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. 23-RESID-POST-AA
    6. 48733
    Prev
    Next
    INDEX
    Explanations

    Financial transactions

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ಕನ್ನಡ
    -0.10
     Uzbek
    -0.09
     البريد
    -0.09
    医保
    -0.09
     이메일
    -0.09
     Laundry
    -0.09
     courrier
    -0.09
     Rent
    -0.09
    .salary
    -0.09
     Emails
    -0.09
    POSITIVE LOGITS
     acquiring
    0.15
     adquir
    0.13
     merchant
    0.11
    merchant
    0.11
     cv
    0.11
     CV
    0.11
     ac
    0.11
     PCI
    0.11
     अध
    0.11
     EM
    0.11
    Activations Density 0.018%

    No Known Activations