Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54997
    Prev
    Next
    INDEX
    Explanations

    draw

    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
    hid
    -0.08
    mb
    -0.07
    GB
    -0.07
    fir
    -0.07
    -valu
    -0.07
     syn
    -0.07
    iit
    -0.07
    138
    -0.07
    -arụ
    -0.07
    hb
    -0.07
    POSITIVE LOGITS
     Roulette
    0.10
     probabilities
    0.09
     couleur
    0.08
     trả
    0.08
     وا
    0.08
     విద్య
    0.08
    的彩票
    0.08
     roulette
    0.08
     مجانية
    0.08
     مشکلات
    0.08
    Activations Density 0.007%

    No Known Activations