© 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. 68201
    Prev
    Next
    INDEX
    Explanations

    sampling

    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
     competit
    -0.07
     competitivo
    -0.07
    -0.07
    \
    -0.07
    励
    -0.07
    (
    -0.07
     gane
    -0.07
    роф
    -0.07
     ganó
    -0.07
     chế
    -0.07
    POSITIVE LOGITS
     목록
    0.10
     리스트
    0.09
    一覧
    0.09
     listar
    0.09
     তাল
    0.09
    全集
    0.09
     सूची
    0.09
    名单
    0.08
    mention
    0.08
    arians
    0.08
    Activations Density 0.018%
    No Known Activations