© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31114
    Prev
    Next
    INDEX
    Explanations

    cell phones

    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
     நட
    -0.08
    是不是
    -0.08
    atar
    -0.08
     previously
    -0.08
    Tel
    -0.08
     Leicester
    -0.07
     നട
    -0.07
     detect
    -0.07
    lio
    -0.07
     ditu
    -0.07
    POSITIVE LOGITS
    (mesh
    0.09
     mesh
    0.09
     internationaux
    0.09
     international
    0.08
     projectile
    0.08
     міжнарод
    0.08
     internacional
    0.08
     offseason
    0.08
     internationale
    0.08
     eaux
    0.08
    Activations Density 0.007%

    No Known Activations