© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 99237
    Prev
    Next
    INDEX
    Explanations

    materials

    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
     गतिविध
    -0.10
    activities
    -0.10
     aktivitas
    -0.09
     activity
    -0.09
    _activity
    -0.09
     окно
    -0.09
    Actividad
    -0.09
    actividad
    -0.08
     activities
    -0.08
     अभिनय
    -0.08
    POSITIVE LOGITS
     coatings
    0.16
     materials
    0.15
    材
    0.14
     coating
    0.14
    材料
    0.14
    materials
    0.13
     изготовления
    0.13
     matériaux
    0.13
     материалов
    0.13
     materialen
    0.13
    Activations Density 0.180%

    No Known Activations