© 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. 99675
    Prev
    Next
    INDEX
    Explanations

    ICD codes

    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
     mellow
    -0.09
     ferry
    -0.09
     harbour
    -0.09
     Sahara
    -0.09
     brillo
    -0.08
     föret
    -0.08
     الساح
    -0.08
     pupp
    -0.08
     fools
    -0.08
     Greenpeace
    -0.08
    POSITIVE LOGITS
     diagnoses
    0.13
    Diagnosis
    0.11
     diagnosis
    0.11
     Diagnosis
    0.10
    Diagnostic
    0.10
    请选择
    0.09
    diagn
    0.09
     diagnose
    0.09
     диагноз
    0.09
    诊
    0.09
    Activations Density 0.013%

    No Known Activations