© 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. 112623
    Prev
    Next
    INDEX
    Explanations

    citations

    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
    (on
    -0.08
    entes
    -0.08
    ()))↵↵
    -0.08
    ))↵↵
    -0.08
    (Double
    -0.08
     correcte
    -0.08
     responsabil
    -0.07
     courrier
    -0.07
     reins
    -0.07
    ႏိုင္
    -0.07
    POSITIVE LOGITS
     Derm
    0.08
     starch
    0.07
    mdi
    0.07
     getenv
    0.07
     sır
    0.07
     Diamond
    0.07
    graphics
    0.07
     Diagram
    0.07
    frastruct
    0.07
     Tissue
    0.07
    Activations Density 0.000%

    No Known Activations