© 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. 91455
    Prev
    Next
    INDEX
    Explanations

    story structure

    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
     mandatario
    -0.09
     comfortably
    -0.08
     кеш
    -0.08
     지정
    -0.08
    Cartney
    -0.08
     συγκεκρι
    -0.07
    anderen
    -0.07
     fácilmente
    -0.07
     aantrekkelijk
    -0.07
     könny
    -0.07
    POSITIVE LOGITS
     culmination
    0.15
     climax
    0.15
     culminating
    0.13
     showdown
    0.12
     culmin
    0.12
    终于
    0.12
    _final
    0.11
    最终
    0.11
     finale
    0.10
    -final
    0.10
    Activations Density 0.065%

    No Known Activations