© 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. 20420
    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
     dédiée
    -0.10
     dedicated
    -0.10
     منف
    -0.10
    专
    -0.10
     dédié
    -0.10
     unieke
    -0.10
     đơn
    -0.09
     לפחות
    -0.09
    Dedicated
    -0.09
     dedicada
    -0.09
    POSITIVE LOGITS
     eleven
    0.13
     υψη
    0.12
     high
    0.12
     उच्च
    0.11
     wysok
    0.11
     উচ্চ
    0.11
    ১১
    0.11
    11
    0.11
     высоким
    0.11
     высок
    0.11
    Activations Density 0.025%

    No Known Activations