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. 58454
    Prev
    Next
    INDEX
    Explanations

    late

    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
    નાં
    -0.09
    ીય
    -0.09
     konnen
    -0.08
    elijkheid
    -0.08
     זאת
    -0.08
    кін
    -0.08
     Lovely
    -0.08
     gelernt
    -0.07
     learnt
    -0.07
     Yay
    -0.07
    POSITIVE LOGITS
    0.08
    10
    0.08
    630
    0.08
    625
    0.08
    629
    0.08
    围
    0.08
    309
    0.08
     reproduce
    0.08
    fra
    0.08
     around
    0.07
    Activations Density 0.023%

    No Known Activations