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. 48767
    Prev
    Next
    INDEX
    Explanations

    co

    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
    Jog
    -0.08
     Abst
    -0.08
     Jog
    -0.08
    Hos
    -0.08
     Wilson
    -0.07
    ijing
    -0.07
     itu
    -0.07
     Hos
    -0.07
     Atkins
    -0.07
    Wilson
    -0.07
    POSITIVE LOGITS
    שה
    0.08
    وال
    0.07
    ూమ
    0.07
     romance
    0.07
     spear
    0.07
    -bordered
    0.07
    สร้าง
    0.07
     اخیر
    0.07
    animate
    0.07
     helpless
    0.07
    Activations Density 0.006%

    No Known Activations