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. 105961
    Prev
    Next
    INDEX
    Explanations

    graph theory/math 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
     ਵਾਲ
    -0.09
    Red
    -0.08
    Tong
    -0.07
    ə
    -0.07
    랙
    -0.07
     trauma
    -0.07
    Ho
    -0.07
    hic
    -0.07
    인트
    -0.07
    mlich
    -0.07
    POSITIVE LOGITS
    都有
    0.11
     alike
    0.10
     excepto
    0.10
    _except
    0.09
     participates
    0.09
     đều
    0.09
     uniformly
    0.09
     except
    0.08
     behalve
    0.08
     gleicher
    0.08
    Activations Density 0.042%

    No Known Activations