© 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. 7-RESID-POST-AA
    11. 939
    Prev
    Next
    INDEX
    Explanations

    是

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بق
    -0.07
     timers
    -0.07
     பே
    -0.07
     fundamentally
    -0.07
    இ
    -0.07
     substr
    -0.07
    (dat
    -0.07
     appe
    -0.07
     buong
    -0.06
     Stuff
    -0.06
    POSITIVE LOGITS
    anko
    0.08
    לים
    0.07
     Avi
    0.07
    ornado
    0.07
     solt
    0.07
     remedy
    0.07
    Ins
    0.07
     normalen
    0.07
    angar
    0.07
     mantra
    0.07
    Activations Density 0.000%

    No Known Activations