Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 43962
    Prev
    Next
    INDEX
    Explanations

    takeaways

    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
     hail
    -0.07
    Ifc
    -0.07
    ment
    -0.07
     centrifugal
    -0.07
     COST
    -0.07
    పై
    -0.07
    �
    -0.07
    ifi
    -0.07
    	↵↵↵
    -0.07
    126
    -0.07
    POSITIVE LOGITS
    >The
    0.09
     firstly
    0.08
     Firstly
    0.08
     clásico
    0.08
     Develop
    0.08
     สำ
    0.08
     มี
    0.07
    .dg
    0.07
     elder
    0.07
     ต้อง
    0.07
    Activations Density 0.011%

    No Known Activations