© 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. 11-RESID-POST-AA
    11. 31513
    Prev
    Next
    INDEX
    Explanations

    lighting

    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
     Everton
    -0.10
     налич
    -0.08
     Reid
    -0.08
     Fuk
    -0.08
    Ki
    -0.08
     Leicester
    -0.08
     Blackboard
    -0.07
     mosaic
    -0.07
     Ease
    -0.07
    Ease
    -0.07
    POSITIVE LOGITS
     carn
    0.08
    Photography
    0.08
     illuminating
    0.08
     spray
    0.08
     severely
    0.08
     രംഗ
    0.07
    自然
    0.07
    照片
    0.07
     bath
    0.07
    写真
    0.07
    Activations Density 0.004%

    No Known Activations