Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 98956
    Prev
    Next
    INDEX
    Explanations

    exhibit design

    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
     Haushalt
    -0.09
     ఇద్ద
    -0.09
     kehid
    -0.09
     vrede
    -0.09
     gambler
    -0.08
     bestätigt
    -0.08
     addictions
    -0.08
     wives
    -0.08
     tekenen
    -0.08
     الزوج
    -0.08
    POSITIVE LOGITS
     музей
    0.10
     multimedia
    0.10
     мероприятия
    0.10
     прозрач
    0.09
     transparent
    0.09
    Transparent
    0.09
     kios
    0.09
     museum
    0.09
     materials
    0.09
     visitors
    0.09
    Activations Density 0.042%

    No Known Activations