© 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. 11-RESID-POST-AA
    11. 68896
    Prev
    Next
    INDEX
    Explanations

    emotional intelligence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحوار
    -0.09
     filming
    -0.08
    .mall
    -0.08
     monst
    -0.08
    ět
    -0.08
     relieved
    -0.08
    astre
    -0.07
     tevoren
    -0.07
    номер
    -0.07
     divorce
    -0.07
    POSITIVE LOGITS
     자기
    0.08
     पहल
    0.07
    ucional
    0.07
    Deserialize
    0.07
    र
    0.07
     inferior
    0.07
    ateral
    0.07
     lé
    0.07
    existing
    0.07
     khả
    0.07
    Activations Density 0.002%

    No Known Activations