© 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. 78400
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     foreign
    -0.09
     assets
    -0.08
     intoxic
    -0.08
     antiques
    -0.08
     infection
    -0.08
     influenza
    -0.08
     chronological
    -0.08
     infestation
    -0.07
    UICollection
    -0.07
    -0.07
    POSITIVE LOGITS
     पसंद
    0.09
     রেখ
    0.08
     centroid
    0.08
     शी
    0.08
    (px
    0.08
     мөр
    0.08
    ogenerated
    0.08
    사항
    0.08
     werde
    0.08
     px
    0.07
    Activations Density 0.030%
    No Known Activations