© 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. 45446
    Prev
    Next
    INDEX
    Explanations

    Ratios

    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
     harassment
    -0.08
     accidentes
    -0.08
     tecnologías
    -0.07
     réseaux
    -0.07
     uim
    -0.07
     pneus
    -0.07
     uitgebreide
    -0.07
    orset
    -0.07
    éns
    -0.07
    锦
    -0.07
    POSITIVE LOGITS
     başlay
    0.09
     ओर
    0.09
    aptop
    0.08
    開始
    0.08
    ’ordre
    0.08
     البداية
    0.08
     loyalty
    0.08
     شروع
    0.08
     시작
    0.07
     orderly
    0.07
    Activations Density 0.028%

    No Known Activations