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. 56243
    Prev
    Next
    INDEX
    Explanations

    drug tests

    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
    χι
    -0.08
     propagation
    -0.08
     widgets
    -0.08
     влож
    -0.08
     parall
    -0.08
     dialogues
    -0.08
    \Column
    -0.08
     Tripadvisor
    -0.08
    .parallel
    -0.08
    Sibling
    -0.08
    POSITIVE LOGITS
    检测
    0.16
     urine
    0.12
     detectable
    0.11
     detection
    0.11
     biometric
    0.10
     adulter
    0.10
    Detection
    0.10
     detox
    0.10
     Detect
    0.10
     forensic
    0.10
    Activations Density 0.019%

    No Known Activations