© 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 EvalsExportsinterp-engineNEWAPI 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. 51387
    Prev
    Next
    INDEX
    Explanations

    复

    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
    (class
    -0.08
    анч
    -0.08
    <Class
    -0.07
     मंज
    -0.07
    class
    -0.07
    <class
    -0.07
    bed
    -0.07
     asociación
    -0.07
    	class
    -0.07
    clazz
    -0.07
    POSITIVE LOGITS
     reproduce
    0.23
     reproduction
    0.22
     reproduced
    0.21
     replicate
    0.21
     reprodu
    0.21
     reproduc
    0.20
     reprodução
    0.20
     replic
    0.20
    produce
    0.19
     reproducción
    0.19
    Activations Density 0.006%

    No Known Activations