© 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. 99278
    Prev
    Next
    INDEX
    Explanations

    avoid

    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
    ensity
    -0.08
    -about
    -0.08
     gekocht
    -0.07
     válido
    -0.07
     Nelson
    -0.07
    -down
    -0.07
    秋
    -0.07
    woman
    -0.07
     {.
    -0.07
     tur
    -0.07
    POSITIVE LOGITS
     pitfalls
    0.12
     excessive
    0.09
     confl
    0.09
    ably
    0.09
     reinvent
    0.09
     undue
    0.09
     costly
    0.08
     Pit
    0.08
     unnecessary
    0.08
     confusion
    0.08
    Activations Density 0.020%

    No Known Activations