© 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. 95600
    Prev
    Next
    INDEX
    Explanations

    packing for travel

    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
     cherish
    -0.08
     commercially
    -0.08
     балки
    -0.07
     pi
    -0.07
     blat
    -0.07
     ©
    -0.07
     Dib
    -0.07
     Jimmy
    -0.07
     rik
    -0.07
     publiceren
    -0.07
    POSITIVE LOGITS
     itinerary
    0.09
     toiletries
    0.08
     laundering
    0.08
     cloth
    0.08
    cloth
    0.08
     Mixing
    0.08
    模板
    0.08
    lichen
    0.08
     saur
    0.07
     stylesheet
    0.07
    Activations Density 0.016%

    No Known Activations