© 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. 21611
    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
     lis
    -0.08
     sumus
    -0.07
    istle
    -0.07
     volna
    -0.07
     than
    -0.07
     vs
    -0.07
     CALL
    -0.07
     retina
    -0.07
    ORIZATION
    -0.07
     nette
    -0.07
    POSITIVE LOGITS
    ările
    0.09
    allos
    0.08
     दोनों
    0.08
     zowel
    0.08
    "errors
    0.08
     उच्च
    0.08
    תגובות
    0.08
    érez
    0.08
     один
    0.08
     उनी
    0.08
    Activations Density 0.003%

    No Known Activations