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. 8492
    Prev
    Next
    INDEX
    Explanations

    math word problems

    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
     ώστε
    -0.07
    )new
    -0.07
     imagination
    -0.07
    ోహ
    -0.07
    ಗೆ
    -0.07
     postura
    -0.07
    ọwọ
    -0.07
     dign
    -0.07
    american
    -0.07
    crow
    -0.06
    POSITIVE LOGITS
     hingegen
    0.10
    則
    0.08
     అదే
    0.08
     naman
    0.08
     likewise
    0.07
     прыг
    0.07
     BJ
    0.07
     isə
    0.07
    са
    0.07
     levam
    0.07
    Activations Density 0.048%

    No Known Activations