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

    Neuronpedia

    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. 78105
    Prev
    Next
    INDEX
    Explanations

    noodle

    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
     libero
    -0.08
    Instead
    -0.08
    Provides
    -0.07
     Dominican
    -0.07
    adz
    -0.07
    /web
    -0.07
     too
    -0.07
    Too
    -0.07
    "))↵↵
    -0.07
    odz
    -0.07
    POSITIVE LOGITS
     samarbe
    0.09
     facts
    0.08
     fakta
    0.08
     Excav
    0.08
     Facts
    0.08
     carriage
    0.08
     bæ
    0.08
     ਰਹ
    0.08
     ilişk
    0.08
     Croix
    0.08
    Activations Density 0.009%

    No Known Activations