© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 94826
    Prev
    Next
    INDEX
    Explanations

    multiple births

    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
    .view
    -0.08
     subtitle
    -0.08
     hon
    -0.08
    VIEW
    -0.08
    mapped
    -0.07
     lwm
    -0.07
    ビュー
    -0.07
     danger
    -0.07
     tł
    -0.07
    ='#
    -0.07
    POSITIVE LOGITS
     outfits
    0.09
     outfit
    0.08
     pants
    0.08
    uous
    0.08
    
    0.08
    라도
    0.08
     Debbie
    0.08
     八
    0.07
     пола
    0.07
    yz
    0.07
    Activations Density 0.003%

    No Known Activations