© 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. 19-RESID-POST-AA
    11. 19095
    Prev
    Next
    INDEX
    Explanations

    say ending "+"

    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
     tầng
    -0.08
     wou
    -0.08
    专业
    -0.08
     labores
    -0.08
    	do
    -0.07
    τηση
    -0.07
     lì
    -0.07
    	self
    -0.07
     utilisant
    -0.07
    	match
    -0.07
    POSITIVE LOGITS
    -three
    0.11
    )-(
    0.10
    -four
    0.09
    ()-
    0.09
    -six
    0.09
    ,-
    0.09
    -five
    0.08
    -two
    0.08
     三
    0.08
     tablespoons
    0.08
    Activations Density 0.007%

    No Known Activations