© 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. 71033
    Prev
    Next
    INDEX
    Explanations

    Providing advice about earning 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
     staining
    -0.09
     색
    -0.09
     bordo
    -0.09
     specimens
    -0.09
     receptors
    -0.08
     Allergy
    -0.08
     Seating
    -0.08
     pels
    -0.08
     radians
    -0.08
     itk
    -0.08
    POSITIVE LOGITS
    赚钱
    0.20
    创业
    0.18
    赚
    0.17
     entrepreneurial
    0.17
     entrepreneurship
    0.16
    挣钱
    0.15
     lucrative
    0.14
     empreendedor
    0.14
     entrepreneur
    0.14
     profitable
    0.13
    Activations Density 0.052%

    No Known Activations