Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43715
    Prev
    Next
    INDEX
    Explanations

    insulin

    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
    楽し
    -0.09
    ご了承ください
    -0.09
    築
    -0.08
     Bald
    -0.08
     edgy
    -0.08
     flea
    -0.08
     Monet
    -0.07
    _FB
    -0.07
    ไหน
    -0.07
    ๆ
    -0.07
    POSITIVE LOGITS
     doses
    0.08
    otrans
    0.08
    _needed
    0.08
    Needed
    0.08
     Im
    0.07
     glucose
    0.07
     г
    0.07
     sulfate
    0.07
     cot
    0.07
     tí
    0.07
    Activations Density 0.002%

    No Known Activations