© 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. 44487
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    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
     miles
    -0.09
     ages
    -0.07
     Fernando
    -0.07
     Harris
    -0.07
     Verlauf
    -0.07
     Helsing
    -0.07
     развлеч
    -0.07
    Merged
    -0.07
     возраст
    -0.07
    Hand
    -0.07
    POSITIVE LOGITS
     hierbij
    0.09
     hesitation
    0.08
     QApplication
    0.08
     输出
    0.08
     đúng
    0.08
     ting
    0.08
     hieronder
    0.08
     hes
    0.08
    īga
    0.08
     jeśli
    0.07
    Activations Density 0.000%

    No Known Activations