© 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. 103201
    Prev
    Next
    INDEX
    Explanations

    period

    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
     latter
    -0.10
     such
    -0.09
     tels
    -0.08
    ↵↵
    -0.08
     final
    -0.08
     additional
    -0.08
     improved
    -0.08
     latest
    -0.08
    дений
    -0.08
     arquivos
    -0.07
    POSITIVE LOGITS
    0
    0.09
    straight
    0.09
    -It
    0.08
     అది
    0.08
    IAL
    0.08
     όχι
    0.08
    Teach
    0.08
    -specific
    0.08
    Pipe
    0.08
    ueless
    0.07
    Activations Density 0.001%

    No Known Activations