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. 87810
    Prev
    Next
    INDEX
    Explanations

    repeating decimal fractions

    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
    Collapse
    -0.09
    Serial
    -0.08
     nack
    -0.08
    Collapsed
    -0.08
     lika
    -0.08
    Brands
    -0.08
     bra
    -0.07
     HAD
    -0.07
    访
    -0.07
     Collapse
    -0.07
    POSITIVE LOGITS
     naturellement
    0.08
     Sands
    0.07
     naturally
    0.07
     naturalmente
    0.07
     Mouth
    0.07
     statue
    0.07
     trio
    0.07
    :
    0.07
     summer
    0.07
     сам
    0.07
    Activations Density 0.001%

    No Known Activations