© 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. 94371
    Prev
    Next
    INDEX
    Explanations

    Survival

    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
     हमें
    -0.08
    isco
    -0.08
     tailoring
    -0.07
    Buffered
    -0.07
     glance
    -0.07
     näht
    -0.07
     tuning
    -0.07
    Allowance
    -0.07
     tails
    -0.07
    tail
    -0.07
    POSITIVE LOGITS
     hidup
    0.09
    生活
    0.08
     kubva
    0.08
    攻略
    0.07
     supernatural
    0.07
     survival
    0.07
     госп
    0.07
     precar
    0.07
    暮
    0.07
     Oromoo
    0.07
    Activations Density 0.006%

    No Known Activations