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. 23-RESID-POST-AA
    6. 98452
    Prev
    Next
    INDEX
    Explanations

    par

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    으로
    -0.09
    हरा
    -0.09
     வீட்ட
    -0.08
    (long
    -0.08
    =z
    -0.08
     converge
    -0.08
     மூலம்
    -0.08
    Por
    -0.08
     verschill
    -0.08
    (gray
    -0.08
    POSITIVE LOGITS
    mi
    0.12
     opposition
    0.11
    ler
    0.10
     ex
    0.10
    all
    0.10
    adox
    0.09
    leb
    0.09
    lers
    0.09
    ag
    0.08
    cours
    0.08
    Activations Density 0.001%

    No Known Activations