© 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. 11-RESID-POST-AA
    11. 99263
    Prev
    Next
    INDEX
    Explanations

    the

    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
     миру
    -0.07
    predict
    -0.07
     _
    -0.07
     networks
    -0.07
    614
    -0.07
     réseaux
    -0.07
     spreadsheets
    -0.07
     ří
    -0.06
     Real
    -0.06
    >\<
    -0.06
    POSITIVE LOGITS
     reluctantly
    0.09
    欢
    0.09
     thaw
    0.08
    anak
    0.08
    weile
    0.08
    -toast
    0.08
     selesai
    0.08
     laughter
    0.08
    anw
    0.08
     workable
    0.08
    Activations Density 0.033%

    No Known Activations