© 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. 18123
    Prev
    Next
    INDEX
    Explanations

    opsis

    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
    .UU
    -0.08
     Buick
    -0.08
    corded
    -0.08
    ạch
    -0.08
     feline
    -0.07
    оц
    -0.07
    ografie
    -0.07
     Hewlett
    -0.07
    كنولوج
    -0.07
    .Managed
    -0.07
    POSITIVE LOGITS
     posibles
    0.08
     denna
    0.08
    .event
    0.08
     dəfə
    0.08
     test
    0.08
     posible
    0.08
    	sleep
    0.08
    	test
    0.08
     olsun
    0.08
    Evento
    0.07
    Activations Density 0.002%

    No Known Activations