© 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. 45494
    Prev
    Next
    INDEX
    Explanations

    root finding calculations

    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
    تیا
    -0.09
     unions
    -0.08
     worldview
    -0.08
    -empty
    -0.07
     centralized
    -0.07
     digo
    -0.07
    ایا
    -0.07
     worldly
    -0.07
     Directed
    -0.07
     vier
    -0.07
    POSITIVE LOGITS
     optimum
    0.09
    ≈
    0.09
     refine
    0.09
    Interpol
    0.09
    Iterations
    0.09
     approximately
    0.08
    équ
    0.08
     pinpoint
    0.08
    Approximately
    0.08
    _estim
    0.08
    Activations Density 0.018%

    No Known Activations