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. 45830
    Prev
    Next
    INDEX
    Explanations

    Key

    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
    _constants
    -0.09
     unpleasant
    -0.08
     любого
    -0.08
     fixation
    -0.08
     FIX
    -0.08
    instr
    -0.08
     સિવ
    -0.08
     depende
    -0.08
     [-
    -0.08
     зависит
    -0.08
    POSITIVE LOGITS
     successful
    0.09
     त्यांनी
    0.09
     renowned
    0.08
     उन्होंने
    0.08
    Successful
    0.08
     അവർ
    0.08
     year
    0.08
     founded
    0.08
     scandal
    0.08
     성공
    0.08
    Activations Density 0.037%

    No Known Activations