© 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. 30408
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     ся
    -0.08
     Rover
    -0.08
     forgetting
    -0.08
     اهمیت
    -0.08
    Conven
    -0.07
     maje
    -0.07
     основных
    -0.07
     crucial
    -0.07
     rehe
    -0.07
     গুরুত্বপূর্ণ
    -0.07
    POSITIVE LOGITS
     chopped
    0.09
     Sushi
    0.08
     diced
    0.08
     combinations
    0.08
     freshly
    0.08
     Turkey
    0.07
     Garden
    0.07
    овая
    0.07
     frais
    0.07
     Fiscal
    0.07
    Activations Density 0.026%

    No Known Activations