© 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. 21211
    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
    obald
    -0.09
    (Guid
    -0.08
    ;;;;
    -0.08
     (%
    -0.08
     implementation
    -0.08
     sekal
    -0.08
     कहल
    -0.08
     дозвол
    -0.07
    -designed
    -0.07
    "./
    -0.07
    POSITIVE LOGITS
     max
    0.11
     attained
    0.10
    max
    0.10
    =max
    0.10
    	max
    0.10
     occurs
    0.09
     발생
    0.09
     valore
    0.09
     value
    0.09
     among
    0.09
    Activations Density 0.013%

    No Known Activations