© 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. 110953
    Prev
    Next
    INDEX
    Explanations

    tax refunds

    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
     beschäftigen
    -0.07
     distinguir
    -0.07
     стратегии
    -0.07
    _mark
    -0.07
     célébr
    -0.07
     coupe
    -0.07
    руд
    -0.07
    'ol
    -0.07
    ушки
    -0.07
    _nf
    -0.07
    POSITIVE LOGITS
     refund
    0.14
     refunded
    0.13
     refunds
    0.13
     refundable
    0.13
    退款
    0.11
    返
    0.11
     Refund
    0.11
    refund
    0.11
     surplus
    0.10
     rebate
    0.10
    Activations Density 0.024%

    No Known Activations