© 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. 102178
    Prev
    Next
    INDEX
    Explanations

    should

    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
     ensures
    -0.10
     ensured
    -0.10
    ,
    -0.10
     सुनिश्चित
    -0.10
     möglicherweise
    -0.10
     unique
    -0.09
     standard
    -0.09
     wellicht
    -0.08
    ensure
    -0.08
     guaranteed
    -0.08
    POSITIVE LOGITS
     have
    0.13
     memiliki
    0.12
     terlihat
    0.11
     hebben
    0.10
    ’avoir
    0.10
     Have
    0.10
    'avoir
    0.10
     feels
    0.10
     feel
    0.10
     sentirse
    0.10
    Activations Density 0.006%

    No Known Activations