© 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. 23-RESID-POST-AA
    11. 96405
    Prev
    Next
    INDEX
    Explanations

    Numerical calculations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ვარ
    -0.08
     方
    -0.07
    方
    -0.07
    変
    -0.07
     mul
    -0.07
     շրջան
    -0.07
     Gainesville
    -0.07
     описание
    -0.07
     Giant
    -0.07
    ㎡
    -0.07
    POSITIVE LOGITS
    772
    0.10
    ulling
    0.09
     av
    0.09
     necesitar
    0.08
     necesit
    0.08
    ining
    0.08
     полноцен
    0.08
     diplomatic
    0.08
     sublic
    0.08
    (av
    0.08
    Activations Density 0.001%

    No Known Activations