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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 78379
    Prev
    Next
    INDEX
    Explanations

    and

    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
     elo
    -0.09
    wijs
    -0.08
    альных
    -0.07
     specificity
    -0.07
    aniwang
    -0.07
     justiça
    -0.07
    Blockchain
    -0.07
     dúvidas
    -0.07
    Mun
    -0.07
     пропис
    -0.07
    POSITIVE LOGITS
     möglicherweise
    0.11
     hazardous
    0.11
     may
    0.10
    ご了承ください
    0.09
     eventuell
    0.09
    You'll
    0.09
     있음
    0.09
     you'll
    0.09
     encontrarás
    0.09
     risque
    0.09
    Activations Density 0.111%

    No Known Activations