© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70912
    Prev
    Next
    INDEX
    Explanations

    like-for-like sales

    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
     فیلم
    -0.09
     מאוד
    -0.09
     متفاوت
    -0.08
    にな
    -0.08
     هو
    -0.08
    ăț
    -0.08
    ाय
    -0.08
     tiring
    -0.08
     هما
    -0.08
    作用
    -0.08
    POSITIVE LOGITS
     odstr
    0.08
     benchmarking
    0.08
     comparison
    0.08
     tranny
    0.08
    comparison
    0.08
    [Double
    0.07
     preservar
    0.07
     analisar
    0.07
     nicer
    0.07
     deeln
    0.07
    Activations Density 0.004%

    No Known Activations