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

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 49634
    Prev
    Next
    INDEX
    Explanations

    Habits

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seizoen
    -0.08
    News
    -0.08
     resilience
    -0.07
     fulfilled
    -0.07
     cloned
    -0.07
     news
    -0.07
     servidor
    -0.07
     News
    -0.07
     fulfillment
    -0.07
    68
    -0.07
    POSITIVE LOGITS
    ечес
    0.09
     �
    0.09
    (Border
    0.08
    kwọ
    0.08
     qilib
    0.08
    ғып
    0.08
     թվում
    0.08
    	rect
    0.08
    armik
    0.08
     diý
    0.08
    Activations Density 0.003%

    No Known Activations