© 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. 20112
    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
     respectivos
    -0.09
     함께
    -0.08
    'autres
    -0.08
    নিজ
    -0.08
     שונים
    -0.08
    /or
    -0.08
     respectivas
    -0.08
     다양한
    -0.08
     others
    -0.08
     différentes
    -0.08
    POSITIVE LOGITS
    -अलग
    0.14
     biệt
    0.13
     entities
    0.12
     entity
    0.11
    Entities
    0.11
    _entities
    0.11
    _entity
    0.11
     entidad
    0.11
    Entity
    0.10
     ಆದರೆ
    0.10
    Activations Density 0.015%

    No Known Activations