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. 87969
    Prev
    Next
    INDEX
    Explanations

    fantasy

    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
    Approximately
    -0.08
     bre
    -0.08
    Exponent
    -0.08
    Marriage
    -0.08
    너지
    -0.08
    Bre
    -0.07
     swallowed
    -0.07
    ுந
    -0.07
     rector
    -0.07
     Nose
    -0.07
    POSITIVE LOGITS
     fiction
    0.08
     instrumental
    0.08
    agory
    0.07
    air
    0.07
     chắc
    0.07
    纷
    0.07
    itious
    0.07
    fiction
    0.07
    樂
    0.07
     tabletop
    0.07
    Activations Density 0.007%

    No Known Activations