© 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. 11-RESID-POST-AA
    11. 78181
    Prev
    Next
    INDEX
    Explanations

    Solve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    waren
    -0.09
     Binder
    -0.08
     Conclusions
    -0.08
    绑
    -0.08
    Idle
    -0.08
     sticky
    -0.08
     worship
    -0.07
     Relig
    -0.07
    abbat
    -0.07
     Limb
    -0.07
    POSITIVE LOGITS
     коэффици
    0.08
    alc
    0.08
     solve
    0.08
     Solve
    0.08
     sqrt
    0.08
     typical
    0.08
     undergo
    0.08
    _exact
    0.08
    Solve
    0.08
     locate
    0.08
    Activations Density 0.031%

    No Known Activations