© 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. 6390
    Prev
    Next
    INDEX
    Explanations

    Р

    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
    ges
    -0.08
    èse
    -0.08
    97
    -0.08
    rological
    -0.08
    fuscated
    -0.08
    ging
    -0.08
    jat
    -0.07
    ged
    -0.07
    keras
    -0.07
     côté
    -0.07
    POSITIVE LOGITS
    ЕЛ
    0.12
    ел
    0.11
    ಿಲ
    0.10
    ელ
    0.09
    ెల
    0.09
    аць
    0.09
    િલ
    0.09
    alien
    0.09
    ਿਲ
    0.09
    ில
    0.09
    Activations Density 0.003%

    No Known Activations