© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68504
    Prev
    Next
    INDEX
    Explanations

    So

    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
    もっと
    -0.10
    玩吗
    -0.08
    まだ
    -0.08
     kakhulu
    -0.08
     tanpa
    -0.08
    いい
    -0.08
     ಹೆಚ್ಚು
    -0.08
     కాదు
    -0.08
    ONLY
    -0.07
     nemus
    -0.07
    POSITIVE LOGITS
     बताते
    0.09
     concluded
    0.08
    rụ
    0.08
    hlen
    0.07
     elucid
    0.07
     adsorption
    0.07
     ©
    0.07
     Au
    0.07
     interdisciplinary
    0.07
    0.07
    Activations Density 0.065%

    No Known Activations