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. 43294
    Prev
    Next
    INDEX
    Explanations

    order

    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
     Steel
    -0.08
     steel
    -0.08
     unicorn
    -0.07
     substr
    -0.07
     portals
    -0.07
     TIC
    -0.07
    suffix
    -0.07
    _cmp
    -0.07
    (content
    -0.07
    र्गत
    -0.07
    POSITIVE LOGITS
     altid
    0.08
     Naken
    0.08
     Avrupa
    0.08
    Erot
    0.08
    Euro
    0.08
    peak
    0.08
    .Dialog
    0.08
     genoeg
    0.07
    šanās
    0.07
     DN
    0.07
    Activations Density 0.001%

    No Known Activations