© 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. 50522
    Prev
    Next
    INDEX
    Explanations

    math/programming notation

    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
    particularly
    -0.11
    includes
    -0.10
    including
    -0.09
    	with
    -0.09
    Hence
    -0.09
    (over
    -0.08
    they
    -0.08
    because
    -0.08
    cause
    -0.08
    -0.08
    POSITIVE LOGITS
     Na
    0.09
    0.09
     na
    0.09
     NA
    0.08
     null
    0.08
    Na
    0.08
     zweimal
    0.08
    -benar
    0.08
     la
    0.08
     laj
    0.08
    Activations Density 0.016%

    No Known Activations