© 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. 65024
    Prev
    Next
    INDEX
    Explanations

    );

    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
    ిం�
    -0.07
     connected
    -0.07
     అస
    -0.07
     unlucky
    -0.07
    (connect
    -0.07
     connect
    -0.07
     munk
    -0.07
    andez
    -0.07
     collections
    -0.06
    Daarnaast
    -0.06
    POSITIVE LOGITS
     пищи
    0.08
     बस
    0.08
    uenta
    0.08
     LIGHT
    0.08
     Homemade
    0.08
     nata
    0.08
     खाद
    0.07
    ereal
    0.07
     exhilarating
    0.07
     proizv
    0.07
    Activations Density 0.001%

    No Known Activations