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. 49126
    Prev
    Next
    INDEX
    Explanations

    structured

    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
     પા�
    -0.08
    iol
    -0.08
    mo
    -0.07
    	Command
    -0.07
     является
    -0.07
     io
    -0.07
    	io
    -0.07
     Isabella
    -0.07
     pribadi
    -0.07
     repaired
    -0.07
    POSITIVE LOGITS
     şəkildə
    0.10
    体系
    0.09
     түрде
    0.09
     structured
    0.09
     articul
    0.09
     formal
    0.08
     طریق
    0.08
    auk
    0.08
    Structured
    0.08
     purposeful
    0.08
    Activations Density 0.040%

    No Known Activations