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. 98536
    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cambodian
    -0.10
     Khmer
    -0.09
     Malayalam
    -0.09
    Myanmar
    -0.08
     Burmese
    -0.08
     京都
    -0.08
    Singapore
    -0.08
     Erdoğan
    -0.08
    Tokyo
    -0.08
     Malaysian
    -0.08
    POSITIVE LOGITS
     milho
    0.14
     fique
    0.13
     cancha
    0.12
     tilma
    0.12
     agu
    0.12
     tupu
    0.11
     pup
    0.11
     panela
    0.11
     hu
    0.11
     huit
    0.11
    Activations Density 0.007%

    No Known Activations