© 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. 47715
    Prev
    Next
    INDEX
    Explanations

    filmmaking elements

    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
     rodz
    -0.08
     copyrights
    -0.07
     механизм
    -0.07
     stopper
    -0.07
     Assembly
    -0.07
     नेत
    -0.07
     परिवार
    -0.07
    inyi
    -0.07
    акон
    -0.07
    iameter
    -0.07
    POSITIVE LOGITS
     lighting
    0.11
    Lighting
    0.11
    ternoon
    0.09
    过滤
    0.09
    肤
    0.09
    پرد
    0.09
    lighting
    0.08
     consomm
    0.08
     Lighting
    0.08
     daytime
    0.08
    Activations Density 0.008%

    No Known Activations