© 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. 22318
    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
    	data
    -0.10
     acquired
    -0.09
    IZATION
    -0.09
    ization
    -0.09
    iczne
    -0.09
    ised
    -0.09
     डेटा
    -0.09
     illegally
    -0.08
    isation
    -0.08
    IZED
    -0.08
    POSITIVE LOGITS
     appealing
    0.19
     pleasing
    0.16
     atractivo
    0.15
     aantrekkelijke
    0.15
     stunning
    0.14
     aantrekkelijk
    0.14
     привлекатель
    0.13
     atract
    0.12
     captivating
    0.12
    sprechend
    0.12
    Activations Density 0.003%

    No Known Activations