© 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. 23-RESID-POST-AA
    11. 48576
    Prev
    Next
    INDEX
    Explanations

    ối

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    区
    -0.09
    ður
    -0.08
    赤
    -0.08
     peça
    -0.08
    ðar
    -0.08
    pq
    -0.08
    јед
    -0.08
    ಸು
    -0.08
    件
    -0.08
    ða
    -0.08
    POSITIVE LOGITS
     xử
    0.14
     với
    0.13
     tượng
    0.13
     ứng
    0.11
     thoại
    0.10
     chi
    0.10
     diện
    0.10
     sách
    0.09
     tác
    0.09
    処
    0.09
    Activations Density 0.001%

    No Known Activations