© 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. 64747
    Prev
    Next
    INDEX
    Explanations

    grep

    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
     gift
    -0.08
    파
    -0.07
     toutes
    -0.07
    )sender
    -0.07
    стве
    -0.07
    ింపు
    -0.07
     теле
    -0.07
     ਉ
    -0.07
     PF
    -0.07
     interview
    -0.07
    POSITIVE LOGITS
    hi
    0.09
     mach
    0.08
    ট
    0.08
    חי
    0.07
     livelihood
    0.07
    Woo
    0.07
     Mous
    0.07
    Hi
    0.07
    ordable
    0.07
     hott
    0.07
    Activations Density 0.001%

    No Known Activations