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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 54100
    Prev
    Next
    INDEX
    Explanations

    to

    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
    .PR
    -0.08
    945
    -0.07
     transferring
    -0.07
     xc
    -0.07
     मुफ्त
    -0.07
    ︎
    -0.07
     toez
    -0.07
     xhr
    -0.07
     postul
    -0.07
     __________________
    -0.07
    POSITIVE LOGITS
    ğiniz
    0.09
     implication
    0.09
    来说
    0.08
     görül
    0.08
     Wikipedia
    0.08
    ഗ്
    0.08
    来看
    0.08
     выше
    0.08
     упражнения
    0.08
    ที่จะ
    0.07
    Activations Density 0.012%

    No Known Activations