© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19189
    Prev
    Next
    INDEX
    Explanations

    code data

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الإف
    -0.08
     reiterated
    -0.08
     secondaires
    -0.08
     pseudo
    -0.07
     bất
    -0.07
     (+
    -0.07
    ப்பட்ட
    -0.07
    seudo
    -0.07
     buenas
    -0.07
    FFFFFFFF
    -0.07
    POSITIVE LOGITS
     younger
    0.08
     جيڪا
    0.08
    нач
    0.08
    Venue
    0.08
     Kathleen
    0.08
    874
    0.08
     Dataset
    0.08
    Steve
    0.08
    Audience
    0.08
     কৰক
    0.08
    Activations Density 0.001%

    No Known Activations