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. 173
    Prev
    Next
    INDEX
    Explanations

    also

    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
     inoltre
    -0.12
     또한
    -0.12
     також
    -0.10
     همچنین
    -0.10
     également
    -0.10
     außerdem
    -0.10
     также
    -0.09
     also
    -0.09
     zudem
    -0.09
     também
    -0.09
    POSITIVE LOGITS
     고려
    0.11
    考虑
    0.11
     consider
    0.11
     considerar
    0.11
    Consider
    0.10
     consideration
    0.10
     possibility
    0.10
     Betracht
    0.10
    考
    0.10
     considéré
    0.10
    Activations Density 0.031%

    No Known Activations