© 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. 20762
    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
     situation
    -0.08
     Giants
    -0.07
     Actually
    -0.07
     situación
    -0.07
     situação
    -0.07
    -0.07
    -0.07
     Let's
    -0.07
    (Main
    -0.06
     Situation
    -0.06
    POSITIVE LOGITS
    ographique
    0.17
    ologique
    0.16
    ológica
    0.15
    ystycz
    0.15
    ográfico
    0.14
    ográfica
    0.14
    ologica
    0.13
    ogical
    0.12
    ographiques
    0.12
    deithasol
    0.12
    Activations Density 0.033%
    No Known Activations