© 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. 54640
    Prev
    Next
    INDEX
    Explanations

    wire

    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
     factor
    -0.08
     searchable
    -0.07
     steen
    -0.07
    .factor
    -0.07
    Agency
    -0.07
     META
    -0.07
    factor
    -0.07
    Ты
    -0.07
     institutions
    -0.07
     powerful
    -0.07
    POSITIVE LOGITS
     wires
    0.13
     wiring
    0.12
     Wiring
    0.11
     electrodes
    0.11
     listrik
    0.11
     electricians
    0.11
     elétrica
    0.11
     electrical
    0.11
     solder
    0.11
     الكهربائية
    0.10
    Activations Density 0.017%

    No Known Activations