© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 102182
    Prev
    Next
    INDEX
    Explanations

    light

    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
    deque
    -0.09
    姓
    -0.09
    .Completed
    -0.08
    queue
    -0.08
    _QUEUE
    -0.08
    ordeaux
    -0.08
     disg
    -0.08
     zakup
    -0.08
    ��
    -0.08
    四不像
    -0.08
    POSITIVE LOGITS
     lumière
    0.33
     light
    0.30
     lighting
    0.29
     ış
    0.29
     sunlight
    0.29
     luz
    0.29
     iluminação
    0.29
     प्रकाश
    0.28
     الضوء
    0.27
     illumination
    0.27
    Activations Density 0.100%

    No Known Activations