© 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. 141
    Prev
    Next
    INDEX
    Explanations

    they

    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
     cirka
    -0.09
    ximo
    -0.08
     volgens
    -0.08
    Nacimiento
    -0.07
     ips
    -0.07
    ocio
    -0.07
     ~/.
    -0.07
     someday
    -0.07
    _linux
    -0.07
    คืนนี้
    -0.07
    POSITIVE LOGITS
    强调
    0.10
     purposely
    0.09
     хотят
    0.09
     want
    0.09
     intentionally
    0.09
     চান
    0.09
     möchte
    0.08
     emphas
    0.08
     Prav
    0.08
     intend
    0.08
    Activations Density 0.075%

    No Known Activations