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. 53106
    Prev
    Next
    INDEX
    Explanations

    placement

    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
    ాఖ
    -0.08
     подоб
    -0.08
     adres
    -0.07
     kurul
    -0.07
     attendees
    -0.07
     accession
    -0.07
     shareholders
    -0.07
    खे
    -0.07
     адрес
    -0.07
    ATIVE
    -0.07
    POSITIVE LOGITS
     هو
    0.08
     spacecraft
    0.08
     Ron
    0.07
     Slash
    0.07
     pamph
    0.07
    Gar
    0.07
     Smile
    0.07
     troublesome
    0.07
     Prism
    0.07
     SCI
    0.07
    Activations Density 0.003%

    No Known Activations