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. 98556
    Prev
    Next
    INDEX
    Explanations

    February 29

    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
    ọc
    -0.08
     Nigerian
    -0.08
     conducting
    -0.08
    ilega
    -0.08
     gegense
    -0.08
    illende
    -0.08
    oti
    -0.08
     Bijvoorbeeld
    -0.07
    进行
    -0.07
     Job
    -0.07
    POSITIVE LOGITS
     ekstra
    0.09
    .extra
    0.09
    (extra
    0.09
    -extra
    0.09
    額
    0.09
    _extra
    0.08
    constitutional
    0.08
     appended
    0.08
    Extra
    0.08
     Extra
    0.08
    Activations Density 0.004%

    No Known Activations