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. 112869
    Prev
    Next
    INDEX
    Explanations

    banana

    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
     قل
    -0.09
     EM
    -0.08
    IPPING
    -0.08
    	alpha
    -0.08
     religioso
    -0.08
     apache
    -0.08
    apache
    -0.08
     Во
    -0.07
     تنظيف
    -0.07
     electromagnetic
    -0.07
    POSITIVE LOGITS
     mû
    0.08
     restorative
    0.08
    dn
    0.07
     memoir
    0.07
     smoothies
    0.07
    /Text
    0.07
    .Supplier
    0.07
    obook
    0.07
    obs
    0.07
     �
    0.07
    Activations Density 0.003%

    No Known Activations