© 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. 11-RESID-POST-AA
    11. 7854
    Prev
    Next
    INDEX
    Explanations

    from

    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
     Nuggets
    -0.08
    Fit
    -0.07
    Parity
    -0.07
    Payments
    -0.07
    FER
    -0.07
    mera
    -0.07
    fit
    -0.07
    prit
    -0.07
    trained
    -0.06
     fingers
    -0.06
    POSITIVE LOGITS
     kā
    0.10
     latin
    0.09
     vient
    0.08
     ā
    0.08
    源码
    0.08
     украин
    0.08
     tiếng
    0.08
     лат
    0.08
     источник
    0.08
     ipilẹ
    0.08
    Activations Density 0.007%

    No Known Activations