© 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. 79009
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    attice
    -0.09
     teknoloj
    -0.09
    entesque
    -0.09
     milit
    -0.08
    gada
    -0.08
    álise
    -0.08
    -filled
    -0.08
     tecnológicos
    -0.08
     تجهیز
    -0.08
     ensuing
    -0.08
    POSITIVE LOGITS
    ,:,
    0.09
    lock
    0.07
     weld
    0.07
    ทุก
    0.07
     GAS
    0.07
     credited
    0.07
    өр
    0.07
     matur
    0.07
    ுர
    0.06
     سوم
    0.06
    Activations Density 0.003%

    No Known Activations