© 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. 45315
    Prev
    Next
    INDEX
    Explanations

    ink

    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
     voulais
    -0.08
    批准
    -0.08
     Alloy
    -0.07
    己
    -0.07
     Jour
    -0.07
    wir
    -0.07
     Louvre
    -0.07
     Transmission
    -0.07
     SIMPLE
    -0.07
     stray
    -0.07
    POSITIVE LOGITS
     wahr
    0.09
    _traits
    0.08
     perceived
    0.08
     bezeichnet
    0.08
     económ
    0.08
     traits
    0.08
    traits
    0.08
     нович
    0.08
     perceb
    0.08
     ظهور
    0.08
    Activations Density 0.003%

    No Known Activations