© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18087
    Prev
    Next
    INDEX
    Explanations

    HTML/CSS code

    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
    Negative Logits
     Aspire
    -0.09
     Hate
    -0.08
    Instance
    -0.08
    Inp
    -0.08
    Placeholder
    -0.07
     facade
    -0.07
     instance
    -0.07
     imitation
    -0.07
    	instance
    -0.07
    Eligible
    -0.07
    POSITIVE LOGITS
     өндөр
    0.10
     splitter
    0.09
     રાજકોટ
    0.09
     ഉയ
    0.09
     உயர
    0.09
     მაღალი
    0.09
    ებდა
    0.09
     ઉચ્ચ
    0.09
     ნამდვილად
    0.08
     ҳат
    0.08
    Activations Density 0.002%

    No Known Activations