© 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. 102241
    Prev
    Next
    INDEX
    Explanations

    Independence

    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
     never
    -0.07
     embedded
    -0.07
     least
    -0.07
    ്ക
    -0.07
     higher
    -0.07
    末
    -0.07
    Least
    -0.07
     immersed
    -0.07
     abstract
    -0.07
    ्यात
    -0.07
    POSITIVE LOGITS
     indip
    0.17
     indépendante
    0.16
     onafhankelijk
    0.16
     independiente
    0.16
     indépendant
    0.15
     independently
    0.15
     самостоятельно
    0.15
     indépend
    0.15
     independente
    0.15
     zelfstandig
    0.15
    Activations Density 0.016%

    No Known Activations