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. 15-RESID-POST-AA
    6. 19391
    Prev
    Next
    INDEX
    Explanations

    ellipses

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     конкрет
    -0.09
    -books
    -0.08
     konkr
    -0.08
    .news
    -0.08
     /*!↵
    -0.08
    õe
    -0.08
     consci
    -0.08
    zoeken
    -0.08
    .food
    -0.08
    ’urgence
    -0.08
    POSITIVE LOGITS
    ...,
    0.09
     counter
    0.08
     because
    0.08
    ...'
    0.08
     ځکه
    0.08
     porque
    0.07
    ...
    0.07
    ...\
    0.07
    ........
    0.07
     omdat
    0.07
    Activations Density 0.020%

    No Known Activations