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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29747
    Prev
    Next
    INDEX
    Explanations

    Motion capture and screen technology

    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
    شرة
    -0.08
     Fellows
    -0.07
    аби
    -0.07
     incision
    -0.07
    registry
    -0.07
    ••
    -0.07
    ્ર
    -0.07
    ominations
    -0.07
     Arrow
    -0.07
    -0.07
    POSITIVE LOGITS
     nek
    0.08
    sst
    0.08
    ZO
    0.08
     зон
    0.08
     watched
    0.08
     vakant
    0.08
     dol
    0.08
     poul
    0.07
    zeni
    0.07
    الي
    0.07
    Activations Density 0.001%
    No Known Activations