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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 44098
    Prev
    Next
    INDEX
    Explanations

    in good standing

    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
    ుకు
    -0.09
     crease
    -0.08
    రం
    -0.08
    river
    -0.08
    (reader
    -0.08
    .detail
    -0.08
     CRM
    -0.08
    ieft
    -0.08
    171
    -0.07
    aurus
    -0.07
    POSITIVE LOGITS
    良
    0.12
     goodwill
    0.11
    Good
    0.10
     good
    0.10
    good
    0.10
     جيدة
    0.10
     ಉತ್ತಮ
    0.09
     �
    0.09
    _good
    0.09
     Good
    0.09
    Activations Density 0.010%

    No Known Activations