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. 53153
    Prev
    Next
    INDEX
    Explanations

    steals

    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
    arding
    -0.08
    ғыс
    -0.08
     scarcely
    -0.08
     терп
    -0.08
    UPDATE
    -0.08
     经纬
    -0.08
    ارى
    -0.08
     التهاب
    -0.08
    árez
    -0.08
     الوف
    -0.08
    POSITIVE LOGITS
    盗
    0.10
     steals
    0.09
    (enemy
    0.09
     envy
    0.08
     steal
    0.08
     nri
    0.08
     ആക്രമ
    0.08
     malicious
    0.08
     चोरी
    0.08
     stealing
    0.08
    Activations Density 0.001%

    No Known Activations