© 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. 7835
    Prev
    Next
    INDEX
    Explanations

    file paths

    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
     decree
    -0.08
    凝
    -0.08
     consent
    -0.08
     Deborah
    -0.08
     discerning
    -0.08
     débat
    -0.08
     التداول
    -0.08
     infused
    -0.08
     AMG
    -0.08
     considère
    -0.08
    POSITIVE LOGITS
    _relative
    0.14
     relative
    0.13
     Relative
    0.12
     '../../
    0.12
    路径
    0.12
    relative
    0.11
    Relative
    0.11
     "../../
    0.11
     relativa
    0.11
     relativo
    0.11
    Activations Density 0.012%

    No Known Activations