© 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. 77829
    Prev
    Next
    INDEX
    Explanations

    House

    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
     cores
    -0.08
     emin
    -0.08
     dvs
    -0.08
    cores
    -0.08
     vars
    -0.07
     sær
    -0.07
    曼
    -0.07
     laj
    -0.07
    虫
    -0.07
     spezif
    -0.07
    POSITIVE LOGITS
    odos
    0.08
    _CTRL
    0.08
    ‍य
    0.07
     Beijing
    0.07
    -af
    0.07
    -paced
    0.07
     మా
    0.07
     paced
    0.07
    ','=','
    0.07
     opa
    0.07
    Activations Density 0.034%

    No Known Activations