© 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. 15-RESID-POST-AA
    11. 16704
    Prev
    Next
    INDEX
    Explanations

    opening parenthesis

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achte
    -0.08
     zijde
    -0.08
     receipt
    -0.08
    oref
    -0.08
    receipt
    -0.08
     uomini
    -0.08
    .rich
    -0.07
    िष्ट
    -0.07
     उनका
    -0.07
    örden
    -0.07
    POSITIVE LOGITS
     términos
    0.08
     oak
    0.07
     Assuming
    0.07
    \Event
    0.07
     rented
    0.07
     Choices
    0.07
     termes
    0.07
     näiteks
    0.07
    ?,
    0.07
    (?
    0.07
    Activations Density 0.004%

    No Known Activations