© 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. 5681
    Prev
    Next
    INDEX
    Explanations

    we

    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
     perhaps
    -0.60
     talvez
    -0.58
     möglicherweise
    -0.58
     vielleicht
    -0.56
     quizás
    -0.56
     måske
    -0.55
     kanskje
    -0.54
     možda
    -0.54
     wellicht
    -0.53
     kanske
    -0.53
    POSITIVE LOGITS
    ewise
    0.10
    elihood
    0.10
    vesse
    0.09
    aktadır
    0.07
    muştur
    0.06
    0.06
     simpler
    0.06
    erkt
    0.06
    ehicle
    0.06
    ="../../
    0.06
    Activations Density 1.383%
    No Known Activations