© 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. 3-RESID-POST-AA
    11. 13041
    Prev
    Next
    INDEX
    Explanations

    ously

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    、副
    -0.08
     Nate
    -0.07
     อ
    -0.07
     Oval
    -0.07
     ఉన్న
    -0.07
     Orr
    -0.07
    ogenic
    -0.07
     Tyson
    -0.07
     npe
    -0.07
     Gog
    -0.07
    POSITIVE LOGITS
     Res
    0.07
    adm
    0.07
     impl
    0.07
    _processor
    0.07
    加工
    0.07
     laid
    0.07
    etcode
    0.07
     फल
    0.07
     shoulder
    0.07
    .fast
    0.07
    Activations Density 0.004%

    No Known Activations