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. 30788
    Prev
    Next
    INDEX
    Explanations

    choices

    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
    ە
    -0.08
    -0.08
     средство
    -0.08
     التركي
    -0.08
    ى
    -0.08
    \Tests
    -0.07
     tests
    -0.07
     त्यो
    -0.07
     proof
    -0.07
     wrongdoing
    -0.07
    POSITIVE LOGITS
     indica
    0.08
     [{↵
    0.08
    泊
    0.08
     finish
    0.08
     happier
    0.08
    pawn
    0.08
     Speedway
    0.07
     entidades
    0.07
    _finished
    0.07
    ోల
    0.07
    Activations Density 0.002%

    No Known Activations