© 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. 20450
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gpt-4o-miniTriggered by @tatsatx
    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
     offiziellen
    -0.09
    official
    -0.09
    Official
    -0.09
     رسمی
    -0.09
     official
    -0.08
    ounid
    -0.08
     Official
    -0.08
    ických
    -0.08
    _manual
    -0.08
     direkten
    -0.08
    POSITIVE LOGITS
     etc
    0.08
     multil
    0.07
     Burma
    0.07
    insu
    0.07
     multe
    0.07
     mui
    0.07
     sulfur
    0.07
     code
    0.07
     modeled
    0.07
    алт
    0.07
    Activations Density 0.000%

    No Known Activations