© 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. 23-RESID-POST-AA
    11. 50791
    Prev
    Next
    INDEX
    Explanations

    closing and separation

    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
    ്ഞ
    -0.08
    ாஜ
    -0.08
     rite
    -0.08
     nny
    -0.08
     строг
    -0.08
    ാജ
    -0.08
     олон
    -0.08
     йөр
    -0.07
    ilingual
    -0.07
     чыгар
    -0.07
    POSITIVE LOGITS
     closing
    0.24
    Closing
    0.23
     separation
    0.22
    closing
    0.22
     Closing
    0.21
     closure
    0.21
     Separation
    0.19
     separating
    0.19
     closes
    0.19
     separación
    0.18
    Activations Density 0.067%

    No Known Activations