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. 77353
    Prev
    Next
    INDEX
    Explanations

    angle

    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
     Chap
    -0.08
     Jar
    -0.08
    Ž
    -0.07
    두
    -0.07
    Chap
    -0.07
    Mur
    -0.07
    zipcode
    -0.07
     Graphic
    -0.07
    Door
    -0.07
    home
    -0.07
    POSITIVE LOGITS
     však
    0.08
     प्रतिभ
    0.08
     izv
    0.08
    一下
    0.08
     vand
    0.08
     setback
    0.08
    วิ
    0.07
     cuidadosamente
    0.07
     વરસાદ
    0.07
     bend
    0.07
    Activations Density 0.001%

    No Known Activations