© 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. 19-RESID-POST-AA
    11. 102846
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     instinct
    -0.08
    /copyleft
    -0.08
     luggage
    -0.08
     кардан
    -0.08
     зон
    -0.07
     obliga
    -0.07
     спокойно
    -0.07
     привыч
    -0.07
     الزام
    -0.07
    自由
    -0.07
    POSITIVE LOGITS
     starting
    0.15
     Starting
    0.15
     시작
    0.15
    starting
    0.15
     kezd
    0.14
    Starting
    0.14
    _start
    0.14
     শুরু
    0.14
    (start
    0.13
    -start
    0.13
    Activations Density 0.046%

    No Known Activations