© 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. 21711
    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
     never
    -0.09
     jamás
    -0.09
     не
    -0.09
     কখন
    -0.08
     nunca
    -0.08
    Impossible
    -0.08
    ientos
    -0.07
    ení
    -0.07
     могу
    -0.07
     иногда
    -0.07
    POSITIVE LOGITS
    depend
    0.09
    combine
    0.09
    dependency
    0.09
    ल्या
    0.09
    total
    0.08
     banyere
    0.08
    vendor
    0.08
     dependence
    0.08
     combinação
    0.08
    dependencies
    0.08
    Activations Density 0.000%

    No Known Activations