© 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. 31214
    Prev
    Next
    INDEX
    Explanations

    prices and starting points

    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
     comprises
    -0.08
    ath
    -0.08
     своего
    -0.08
     Helm
    -0.07
    ăț
    -0.07
    genomen
    -0.07
     tive
    -0.07
     mele
    -0.07
     Meio
    -0.07
     informs
    -0.07
    POSITIVE LOGITS
    キャン
    0.08
     erhältlich
    0.08
     €
    0.08
    の商品
    0.08
     affordable
    0.08
     કિંમત
    0.08
    优惠
    0.08
     الأسعار
    0.08
    /max
    0.07
     costo
    0.07
    Activations Density 0.021%

    No Known Activations