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. 77417
    Prev
    Next
    INDEX
    Explanations

    Pictures

    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
     saan
    -0.08
     网
    -0.08
    tsch
    -0.08
     Tengo
    -0.07
     Regulations
    -0.07
    ばん
    -0.07
    pok
    -0.07
     piles
    -0.07
    _GUID
    -0.07
     geom
    -0.07
    POSITIVE LOGITS
    旗下
    0.10
    -owned
    0.09
     kuruluş
    0.08
    Released
    0.08
     comedy
    0.08
     doğ
    0.08
     musicals
    0.08
     embry
    0.08
     vast
    0.08
     Hollywood
    0.07
    Activations Density 0.017%

    No Known Activations