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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26327
    Prev
    Next
    INDEX
    Explanations

    light

    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
    IA
    -0.09
    intersection
    -0.08
     rugged
    -0.08
     intersection
    -0.08
     grammat
    -0.08
     imprim
    -0.08
     interrupted
    -0.08
    검
    -0.07
     veiligheids
    -0.07
     inglês
    -0.07
    POSITIVE LOGITS
    Propagation
    0.10
     propagation
    0.09
    传播
    0.09
     propagated
    0.09
     attenuation
    0.09
     propagate
    0.08
    .remote
    0.08
     penetrate
    0.08
    .social
    0.08
     penetr
    0.08
    Activations Density 0.004%

    No Known Activations