© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20247
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     bonding
    -0.09
     bond
    -0.09
     bonds
    -0.09
     ice
    -0.08
     лед
    -0.08
     ظلم
    -0.08
    ناية
    -0.08
     ijs
    -0.08
     xoog
    -0.08
     hielo
    -0.08
    POSITIVE LOGITS
     availability
    0.41
     disponibilidad
    0.39
     Availability
    0.38
    Availability
    0.38
    availability
    0.37
     disponibilidade
    0.37
     disponibilité
    0.37
     beschikbaar
    0.37
     verfügbar
    0.34
     ઉપલબ્ધ
    0.33
    Activations Density 0.032%

    No Known Activations