© 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. 31282
    Prev
    Next
    INDEX
    Explanations

    Jainism

    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
     Kalou
    -0.08
     waist
    -0.08
    [...,
    -0.08
     wetter
    -0.07
     Waik
    -0.07
     delegation
    -0.07
     üm
    -0.07
     knob
    -0.07
     Broadcasting
    -0.07
     quell
    -0.07
    POSITIVE LOGITS
    plural
    0.09
     plural
    0.08
     кисл
    0.08
    ylene
    0.08
    pliers
    0.08
    ті
    0.08
    Passive
    0.08
     же
    0.08
     ecstatic
    0.07
     Separ
    0.07
    Activations Density 0.001%

    No Known Activations