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. 53146
    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
     stuffing
    -0.10
     carpeting
    -0.09
     rechargeable
    -0.09
     Printable
    -0.09
    Masks
    -0.09
     printable
    -0.09
     FAQs
    -0.08
     Delete
    -0.08
    תה
    -0.08
     Guides
    -0.08
    POSITIVE LOGITS
     chronological
    0.09
    years
    0.09
     years
    0.09
    _year
    0.09
     WWII
    0.09
    年月
    0.09
     chron
    0.09
     decades
    0.09
    -year
    0.08
     year
    0.08
    Activations Density 0.036%

    No Known Activations