© 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. 29290
    Prev
    Next
    INDEX
    Explanations

    Facts and statistics

    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
    Scout
    -0.08
     gratuit
    -0.08
     !!↵
    -0.07
    」です
    -0.07
     zoo
    -0.07
     quốc
    -0.07
     scout
    -0.07
    गर
    -0.07
     clu
    -0.07
     squir
    -0.07
    POSITIVE LOGITS
     declines
    0.10
     sebesar
    0.10
     сниз
    0.09
     consistently
    0.09
     declined
    0.09
     слаб
    0.09
     lag
    0.09
    ，同比
    0.09
     mengalami
    0.09
     increases
    0.09
    Activations Density 0.085%

    No Known Activations