© 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. 68567
    Prev
    Next
    INDEX
    Explanations

    billing and invoicing

    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
     союз
    -0.09
    throw
    -0.09
     accent
    -0.08
     Beginner
    -0.08
     freopen
    -0.08
    .Mutable
    -0.08
     improvis
    -0.08
     NSMutable
    -0.08
    Accent
    -0.08
     CGFloat
    -0.08
    POSITIVE LOGITS
     finalized
    0.11
     finalize
    0.10
     electronically
    0.10
     receipt
    0.10
     완료
    0.09
     إلكتر
    0.09
     consumm
    0.09
    receipt
    0.09
     receipts
    0.09
    Receipt
    0.09
    Activations Density 0.017%

    No Known Activations