© 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. 15-RESID-POST-AA
    11. 16336
    Prev
    Next
    INDEX
    Explanations

    proactive/preventive

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     رشته
    -0.08
    _frag
    -0.08
     cigarettes
    -0.07
     fran
    -0.07
    linewidth
    -0.07
     valide
    -0.07
     Corpor
    -0.07
     Frans
    -0.07
    直接
    -0.07
     personnages
    -0.07
    POSITIVE LOGITS
     proactive
    0.12
     preventive
    0.10
    措施
    0.10
    тив
    0.10
    ческого
    0.10
     подготовки
    0.09
    Rather
    0.09
    ческой
    0.09
    ческих
    0.09
     tədb
    0.09
    Activations Density 0.008%

    No Known Activations