© 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. 22631
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     pertinent
    -0.08
     entsprech
    -0.08
    ved
    -0.08
     appropriate
    -0.08
    	if
    -0.08
     évident
    -0.08
     simpler
    -0.08
     necessary
    -0.08
     requisite
    -0.08
    -existing
    -0.08
    POSITIVE LOGITS
     maximize
    0.33
     minimize
    0.31
     maximizing
    0.28
     minimizes
    0.27
     minimizar
    0.27
     minimizing
    0.27
     maxim
    0.25
    maximize
    0.24
     maximise
    0.22
     Maxim
    0.21
    Activations Density 0.020%

    No Known Activations