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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 99395
    Prev
    Next
    INDEX
    Explanations

    Lab procedures

    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
    thinking
    -0.08
     nuance
    -0.08
     Explore
    -0.08
     crunchy
    -0.08
     celebrating
    -0.07
     सुझ
    -0.07
     tän
    -0.07
     tarot
    -0.07
    idata
    -0.07
     toned
    -0.07
    POSITIVE LOGITS
    测
    0.08
     apparatus
    0.08
     dye
    0.08
     Vergleich
    0.08
     seaw
    0.08
     équip
    0.07
     Oc
    0.07
     Comparison
    0.07
     Integral
    0.07
     centrif
    0.07
    Activations Density 0.015%

    No Known Activations