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. 12759
    Prev
    Next
    INDEX
    Explanations

    ics

    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
     lång
    -0.08
    延期
    -0.08
     اختلاف
    -0.08
    جهزة
    -0.08
    诺
    -0.08
     realización
    -0.08
    Dob
    -0.07
    -expand
    -0.07
    controllers
    -0.07
     চলে
    -0.07
    POSITIVE LOGITS
     ketchup
    0.08
     שבה
    0.08
    рал
    0.08
     ky
    0.08
     waarmee
    0.07
     хоча
    0.07
     psychology
    0.07
     speziell
    0.07
     хотя
    0.07
     две
    0.07
    Activations Density 0.002%

    No Known Activations