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. 12889
    Prev
    Next
    INDEX
    Explanations

    :

    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
    -set
    -0.09
    -network
    -0.08
    _set
    -0.08
    -net
    -0.08
    imation
    -0.07
    -real
    -0.07
    -d
    -0.07
    -demand
    -0.07
    -binding
    -0.07
    .network
    -0.07
    POSITIVE LOGITS
    ▋
    0.09
     જેથી
    0.09
     પડશે
    0.09
     tenzij
    0.09
    <|start|>
    0.08
    या
    0.08
     kindly
    0.08
     künftig
    0.08
    ",
    ↵
    0.08
     recetas
    0.08
    Activations Density 0.005%

    No Known Activations