© 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. 30271
    Prev
    Next
    INDEX
    Explanations

    harmful

    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
     현실
    -0.08
     bağlı
    -0.08
    갑
    -0.08
    세요
    -0.07
     인해
    -0.07
     Declar
    -0.07
    iril
    -0.07
    월
    -0.07
    cruit
    -0.07
     gratification
    -0.07
    POSITIVE LOGITS
     harmful
    0.10
     substances
    0.09
     additives
    0.09
     nuisance
    0.09
    .orm
    0.09
     triglycer
    0.08
     булган
    0.08
     wavelengths
    0.08
     pamusoro
    0.08
     веществ
    0.08
    Activations Density 0.015%

    No Known Activations