© 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. 23-RESID-POST-AA
    11. 96445
    Prev
    Next
    INDEX
    Explanations

    process improvement

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ossier
    -0.08
    _PUBLIC
    -0.07
     GLint
    -0.07
    enci
    -0.07
     जीव
    -0.07
     intermediary
    -0.07
    Interp
    -0.07
    Unsigned
    -0.07
    /auth
    -0.07
    Advertisement
    -0.07
    POSITIVE LOGITS
     melhoria
    0.20
     improvement
    0.20
     Lean
    0.20
     Ka
    0.19
     Improvement
    0.19
     Continuous
    0.19
     continuous
    0.18
    改善
    0.18
     kontinuier
    0.18
    Ka
    0.18
    Activations Density 0.058%

    No Known Activations