© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 95757
    Prev
    Next
    INDEX
    Explanations

    formula

    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
     trained
    -0.08
     polling
    -0.08
     interviewing
    -0.08
     प्रशिक्षण
    -0.08
     grooming
    -0.08
    采访
    -0.08
     enqu
    -0.08
     trainings
    -0.08
     errands
    -0.08
     distractions
    -0.08
    POSITIVE LOGITS
     chemically
    0.12
     molecules
    0.12
    chemical
    0.12
     nomen
    0.12
     ethanol
    0.11
     molecule
    0.11
     hydrogen
    0.11
     mole
    0.11
     molecular
    0.10
     compounds
    0.10
    Activations Density 0.018%

    No Known Activations