Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 131053
    Prev
    Next
    INDEX
    Explanations

    misconduct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metallic
    -0.08
     Fran
    -0.08
     snug
    -0.08
     Daughter
    -0.08
     Ensemble
    -0.08
    Nog
    -0.07
     diap
    -0.07
     iodine
    -0.07
     Compat
    -0.07
     Iso
    -0.07
    POSITIVE LOGITS
     violence
    0.13
     wrongdoing
    0.13
     perpetrators
    0.13
     perpetr
    0.13
    侵犯
    0.12
    犯罪
    0.12
     misconduct
    0.12
     allegations
    0.11
     spree
    0.11
     illicit
    0.11
    Activations Density 0.204%

    No Known Activations