© 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. 5404
    Prev
    Next
    INDEX
    Explanations

    but

    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
    We've
    -0.14
     We've
    -0.12
     We'd
    -0.11
    Yet
    -0.11
     एवं
    -0.10
    You've
    -0.10
    He's
    -0.10
    More
    -0.10
    Thus
    -0.10
     हमने
    -0.10
    POSITIVE LOGITS
     I
    0.20
     אני
    0.15
     ես
    0.12
    ↵↵
    0.12
     I'm
    0.12
     я
    0.11
     لا
    0.11
    I
    0.11
    ↵
    0.11
     હું
    0.11
    Activations Density 0.015%

    No Known Activations