© 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. 94650
    Prev
    Next
    INDEX
    Explanations

    capital/operating expenditure (CAPEX/OPEX)

    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
     unsafe
    -0.08
     upr
    -0.08
     Granny
    -0.08
     Verbindung
    -0.07
     billi
    -0.07
     impaired
    -0.07
     chron
    -0.07
    -0.07
     Saunders
    -0.07
     everywhere
    -0.07
    POSITIVE LOGITS
     расходы
    0.12
     ખર્ચ
    0.12
     expense
    0.11
     expenditure
    0.11
     खर्च
    0.11
     расходов
    0.11
     expenditures
    0.11
     expenses
    0.11
     ചെ
    0.10
    Expense
    0.10
    Activations Density 0.013%
    No Known Activations