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. 15-RESID-POST-AA
    6. 130
    Prev
    Next
    INDEX
    Explanations

    ^

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .na
    -0.08
     地址
    -0.08
     {})
    -0.07
     confi
    -0.07
    /o
    -0.07
     consc
    -0.07
     assicur
    -0.07
     Habit
    -0.07
     />,↵
    -0.07
     tills
    -0.07
    POSITIVE LOGITS
     simplifies
    0.11
    Simpl
    0.10
     simplify
    0.10
    وضح
    0.09
    unikira
    0.09
     проще
    0.09
     simplifying
    0.09
    ‌دهد
    0.09
     bardziej
    0.08
     simpler
    0.08
    Activations Density 0.058%

    No Known Activations