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. 113906
    Prev
    Next
    INDEX
    Explanations

    Sporting match scores

    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
    asu
    -0.07
    cub
    -0.07
    ço
    -0.07
    Useful
    -0.07
     boring
    -0.07
     those
    -0.07
    描
    -0.07
    Ver
    -0.07
    _fact
    -0.07
    Factory
    -0.07
    POSITIVE LOGITS
     Flip
    0.08
     doorstep
    0.08
    itswe
    0.08
     ಜಯ
    0.08
     resultaat
    0.08
     LM
    0.08
     небольшой
    0.08
     Нед
    0.08
     Almost
    0.07
     Typography
    0.07
    Activations Density 0.012%

    No Known Activations