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. 77439
    Prev
    Next
    INDEX
    Explanations

    ac

    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
     operating
    -0.08
    Operating
    -0.08
     Operating
    -0.08
     interchangeable
    -0.08
    -0.07
    mero
    -0.07
    akia
    -0.07
    cla
    -0.07
     inexpensive
    -0.07
    Ks
    -0.07
    POSITIVE LOGITS
     yritt
    0.09
     молод
    0.09
     молодой
    0.09
     esimerkiksi
    0.08
     Ryder
    0.08
    .listen
    0.08
     seur
    0.08
     mlad
    0.08
    .flutter
    0.08
     ரசிக
    0.08
    Activations Density 0.002%

    No Known Activations