© 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. 11-RESID-POST-AA
    11. 110653
    Prev
    Next
    INDEX
    Explanations

    leaving or retiring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginner
    -0.10
     girl
    -0.09
     Spiele
    -0.09
     girl's
    -0.09
     beginners
    -0.09
     Anfänger
    -0.09
    少女
    -0.08
     campsite
    -0.08
     eerie
    -0.08
    哭
    -0.08
    POSITIVE LOGITS
    职位
    0.13
     CEO
    0.13
     CEOs
    0.12
    CEO
    0.12
     executives
    0.11
     resign
    0.11
    .linkedin
    0.11
    董事
    0.11
     MBA
    0.11
     tenure
    0.10
    Activations Density 0.195%

    No Known Activations