© 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. 22762
    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
     remodel
    -0.08
     temprano
    -0.08
     remodeled
    -0.08
     Boilers
    -0.07
    requested
    -0.07
     lied
    -0.07
     времена
    -0.07
     Nk
    -0.07
     sweetheart
    -0.07
     Boyd
    -0.07
    POSITIVE LOGITS
     static
    0.21
    	static
    0.19
    静
    0.19
    static
    0.19
    Static
    0.18
     Static
    0.17
    .static
    0.17
    -static
    0.17
     STATIC
    0.17
    STATIC
    0.17
    Activations Density 0.009%

    No Known Activations