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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111225
    Prev
    Next
    INDEX
    Explanations

    Expenses and money

    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
     Multiple
    -0.08
     multiple
    -0.07
     Src
    -0.07
     Verfahren
    -0.07
     Para
    -0.07
     numbering
    -0.07
    ystals
    -0.07
    ึก
    -0.07
    Para
    -0.07
     enumeration
    -0.07
    POSITIVE LOGITS
     생활
    0.15
    expenses
    0.14
    生活
    0.14
     despesas
    0.14
     expenses
    0.13
    Expenses
    0.13
     gastos
    0.13
     खर्च
    0.12
     اليومية
    0.12
     दैनिक
    0.12
    Activations Density 0.023%

    No Known Activations