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. 23-RESID-POST-AA
    6. 98554
    Prev
    Next
    INDEX
    Explanations

    corporate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ordam
    -0.10
    acency
    -0.08
    maker
    -0.08
    uzzy
    -0.08
    ner
    -0.08
    salt
    -0.08
    kii
    -0.08
    ric
    -0.08
    ologic
    -0.08
    innitus
    -0.08
    POSITIVE LOGITS
     governance
    0.14
    -sponsored
    0.14
     America
    0.13
     wellness
    0.13
     america
    0.12
     espion
    0.12
    责任
    0.12
     Governance
    0.12
    /go
    0.12
     সদর
    0.12
    Activations Density 0.011%

    No Known Activations