© 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. 69884
    Prev
    Next
    INDEX
    Explanations

    objectivity

    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
     superiores
    -0.08
     Stunden
    -0.08
    abling
    -0.08
     verbunden
    -0.08
     secured
    -0.07
    _WR
    -0.07
     supérieure
    -0.07
     Dí
    -0.07
     supérieur
    -0.07
     Valid
    -0.07
    POSITIVE LOGITS
     viewpoint
    0.09
     ವಿದ್ಯಾರ್ಥ
    0.08
     perspective
    0.08
    experienced
    0.08
     ಆ
    0.08
     машина
    0.08
     विद्यार्थी
    0.08
     વિદ્યાર્થી
    0.07
     fn
    0.07
     participant
    0.07
    Activations Density 0.003%

    No Known Activations