© 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. 19786
    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
     oder
    -0.08
    Воз
    -0.08
    Reviewed
    -0.08
    или
    -0.08
    ечки
    -0.08
     Գր
    -0.08
     zusammensch
    -0.08
    Released
    -0.08
    .review
    -0.08
    ерж
    -0.08
    POSITIVE LOGITS
     jailbreak
    0.10
     instruct
    0.09
     malicious
    0.09
     directives
    0.09
     impos
    0.08
     imposing
    0.08
     начале
    0.08
     بداية
    0.08
     imposed
    0.08
     البداية
    0.08
    Activations Density 0.011%

    No Known Activations