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. 112958
    Prev
    Next
    INDEX
    Explanations

    time

    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
     Brink
    -0.07
    াহ
    -0.07
    acin
    -0.07
    tre
    -0.07
     occurs
    -0.07
     hour
    -0.07
    hap
    -0.07
     силу
    -0.07
     Situationen
    -0.07
     zil
    -0.07
    POSITIVE LOGITS
     तय
    0.10
     وط
    0.08
     محد
    0.08
     ABB
    0.08
     решения
    0.08
     konusunda
    0.08
    FRAME
    0.08
     دقیق
    0.08
     manus
    0.08
    ABB
    0.07
    Activations Density 0.031%

    No Known Activations