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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 43499
    Prev
    Next
    INDEX
    Explanations

    short

    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
     대한
    -0.08
     З
    -0.08
     herd
    -0.07
     занятия
    -0.07
     SRC
    -0.07
    .generic
    -0.07
     TRI
    -0.07
    441
    -0.07
     zok
    -0.07
     ymin
    -0.07
    POSITIVE LOGITS
    ที่สุด
    0.09
    reu
    0.09
    issimo
    0.08
    Definitely
    0.08
     جدًا
    0.08
    Even
    0.08
    中文字
    0.08
    Maybe
    0.08
     apology
    0.08
    issimi
    0.07
    Activations Density 0.021%

    No Known Activations