© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 5794
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Galway
    -0.11
     Surrey
    -0.10
     Auckland
    -0.10
     Nuuk
    -0.09
     Edmonton
    -0.09
     Armenia
    -0.09
     County
    -0.09
     Trondheim
    -0.09
     Manitoba
    -0.09
     Latvia
    -0.09
    POSITIVE LOGITS
     Mid
    0.13
     Midwest
    0.13
    Mid
    0.11
     Deep
    0.11
     southeast
    0.11
     Southeast
    0.11
     الجنوب
    0.11
    东
    0.11
     states
    0.11
     东
    0.10
    Activations Density 0.029%

    No Known Activations