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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102845
    Prev
    Next
    INDEX
    Explanations

    =

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tahan
    -0.08
    ശ
    -0.07
     respectivas
    -0.07
    /x
    -0.07
     qualquer
    -0.07
    /her
    -0.07
     ulong
    -0.07
    /MM
    -0.07
     certaine
    -0.07
     diepe
    -0.07
    POSITIVE LOGITS
    世纪
    0.09
     of
    0.09
     Kommune
    0.08
    《
    0.08
    enegro
    0.08
     三国
    0.08
    __)↵↵↵
    0.08
    共和国
    0.08
     Ком
    0.08
     teie
    0.08
    Activations Density 0.013%

    No Known Activations