© 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. 19-RESID-POST-AA
    11. 102343
    Prev
    Next
    INDEX
    Explanations

    "model" in different languages

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \Form
    -0.08
     counted
    -0.08
     floats
    -0.08
     dashed
    -0.08
     rumored
    -0.08
     programmers
    -0.08
    abal
    -0.07
     announced
    -0.07
     weaving
    -0.07
     fans
    -0.07
    POSITIVE LOGITS
     모델
    0.20
    模型
    0.20
     मॉडल
    0.20
     modelos
    0.19
     models
    0.19
    モデル
    0.19
     model
    0.19
     modeli
    0.18
     Models
    0.18
     modèles
    0.18
    Activations Density 0.009%

    No Known Activations