© 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. 5583
    Prev
    Next
    INDEX
    Explanations

    law of cosines

    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
     doubled
    -0.09
     Dou
    -0.09
    ből
    -0.08
    �
    -0.08
    dou
    -0.08
    onu
    -0.08
     Zwei
    -0.08
    double
    -0.08
    Dou
    -0.08
     aspecten
    -0.08
    POSITIVE LOGITS
     взаим
    0.09
    659
    0.09
    互
    0.08
     mutual
    0.08
    529
    0.08
    ADAS
    0.08
    898
    0.08
     interference
    0.08
    互动
    0.08
    861
    0.07
    Activations Density 0.021%

    No Known Activations