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. 120323
    Prev
    Next
    INDEX
    Explanations

    report excerpts

    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
     Oklahoma
    -0.09
    odno
    -0.09
     odk
    -0.09
    <Home
    -0.09
     Engelse
    -0.09
    (glm
    -0.08
    .Foreign
    -0.08
    .Wrap
    -0.08
     англий
    -0.08
     Welsh
    -0.08
    POSITIVE LOGITS
     Countries
    0.09
     WHO
    0.08
     jakarta
    0.08
     sku
    0.08
     clazz
    0.08
     countries
    0.08
     países
    0.08
     CARE
    0.08
     uri
    0.08
     jub
    0.07
    Activations Density 0.040%

    No Known Activations