© 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. 29300
    Prev
    Next
    INDEX
    Explanations

    official social media accounts

    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
    .Split
    -0.08
     principios
    -0.08
     invention
    -0.08
     suspect
    -0.08
     piyas
    -0.07
    .Invariant
    -0.07
     tunne
    -0.07
    Iv
    -0.07
     Principles
    -0.07
    .Arg
    -0.07
    POSITIVE LOGITS
    微信公众号
    0.09
    Ticker
    0.09
     cult
    0.08
     superf
    0.08
    联系我们
    0.08
    nitt
    0.08
    േയ
    0.08
    公众号
    0.08
     cultivating
    0.07
    Newsletter
    0.07
    Activations Density 0.019%

    No Known Activations