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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129471
    Prev
    Next
    INDEX
    Explanations

    bookkeeping

    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
     autoplay
    -0.09
     Sized
    -0.08
     mejoras
    -0.08
     Ул
    -0.08
    高さ
    -0.08
     forbed
    -0.08
     Dense
    -0.08
    .Length
    -0.08
     improvement
    -0.08
     Carousel
    -0.08
    POSITIVE LOGITS
     bookkeeping
    0.14
    账
    0.12
    Invoices
    0.12
    _invoice
    0.12
     ledger
    0.12
    .invoice
    0.12
    _transactions
    0.12
     бухгалтер
    0.12
    invoice
    0.12
     fiscale
    0.11
    Activations Density 0.027%

    No Known Activations