Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 117639
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     jan
    -0.08
    ушы
    -0.07
     الأسهم
    -0.07
     koers
    -0.07
     shafts
    -0.07
     coupons
    -0.07
     المرج
    -0.07
     bring
    -0.07
     scholarships
    -0.07
     were
    -0.07
    POSITIVE LOGITS
     ubiquitous
    0.18
     pervasive
    0.17
     ubi
    0.14
     Everywhere
    0.13
     everywhere
    0.13
     überall
    0.12
    普
    0.12
    every
    0.11
     Every
    0.11
     EVERY
    0.11
    Activations Density 0.189%

    No Known Activations