© 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. 63550
    Prev
    Next
    INDEX
    Explanations

    partakers

    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
     réglementation
    -0.08
     queries
    -0.07
     boundary
    -0.07
     captcha
    -0.07
     Calcul
    -0.07
    f
    -0.07
    OCUS
    -0.07
     calculations
    -0.07
    জন
    -0.06
     Spike
    -0.06
    POSITIVE LOGITS
    分享
    0.19
    共享
    0.17
     sharing
    0.16
     공유
    0.16
     साझा
    0.16
     paylaş
    0.16
     partage
    0.15
     compartir
    0.15
     condiv
    0.15
     分享
    0.15
    Activations Density 0.019%

    No Known Activations