© 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. 19-RESID-POST-AA
    11. 19573
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shortlist
    -0.09
     unbiased
    -0.09
    智
    -0.08
    isip
    -0.08
     intelig
    -0.08
     Wisdom
    -0.08
    กัด
    -0.08
     Intelligence
    -0.08
    靠谱
    -0.08
     Intelig
    -0.08
    POSITIVE LOGITS
     extravagant
    0.27
     ornate
    0.26
     lavish
    0.26
     extravag
    0.25
     flamb
    0.23
     elaborate
    0.23
     embell
    0.19
     elabor
    0.19
     ornament
    0.19
     flashy
    0.18
    Activations Density 0.037%

    No Known Activations