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

    Neuronpedia

    Jacobian LensNEW
    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. 113228
    Prev
    Next
    INDEX
    Explanations

    telepathy

    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
     koş
    -0.09
     правила
    -0.09
     koken
    -0.08
    කි
    -0.08
     keto
    -0.08
     инфраструкт
    -0.08
     cass
    -0.08
     Syracuse
    -0.08
     Oranje
    -0.08
     cookware
    -0.08
    POSITIVE LOGITS
     communication
    0.10
     minds
    0.10
     beings
    0.09
    共享
    0.09
     psychic
    0.09
     comunicación
    0.09
     comunic
    0.09
    Communication
    0.09
     empathy
    0.09
     shared
    0.08
    Activations Density 0.028%

    No Known Activations