© 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 EvalsExportsAPI 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. 20520
    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
     platos
    -0.10
     pratos
    -0.09
     machining
    -0.09
     milling
    -0.09
    	camera
    -0.08
     cámaras
    -0.08
    产权
    -0.08
     garments
    -0.08
     dishes
    -0.08
     mecanismos
    -0.08
    POSITIVE LOGITS
     Suicide
    0.14
     suicide
    0.13
     suicidal
    0.13
     suic
    0.12
     Emotional
    0.11
     псих
    0.11
     Calm
    0.11
     психолог
    0.10
     эмоцион
    0.10
     despair
    0.10
    Activations Density 0.002%

    No Known Activations