© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 65330
    Prev
    Next
    INDEX
    Explanations

    given

    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
     масса
    -0.09
     температура
    -0.08
     terapeut
    -0.08
     بدن
    -0.08
    Gig
    -0.08
    ഖ്യാപ
    -0.08
     Yin
    -0.07
     السي
    -0.07
    صاب
    -0.07
     bienestar
    -0.07
    POSITIVE LOGITS
    -mentioned
    0.08
     circumstances
    0.07
    0.07
     describes
    0.07
     casserole
    0.07
    icks
    0.07
    .proxy
    0.07
     assembl
    0.07
    ners
    0.07
     Proxy
    0.07
    Activations Density 0.018%
    No Known Activations