© 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. 94870
    Prev
    Next
    INDEX
    Explanations

    on

    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
     osób
    -0.09
     Maryland
    -0.08
    ోడ
    -0.08
     pozitiv
    -0.08
     kult
    -0.08
     Yukon
    -0.08
     Alpen
    -0.08
     ছাড়
    -0.08
     jumlah
    -0.08
     Edmonton
    -0.08
    POSITIVE LOGITS
     alsnog
    0.08
     corrupted
    0.07
    重新
    0.07
     solely
    0.07
    .send
    0.07
     truly
    0.07
    Captain
    0.07
     exclusivamente
    0.07
    Found
    0.07
     corrupt
    0.07
    Activations Density 0.004%

    No Known Activations