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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 53303
    Prev
    Next
    INDEX
    Explanations

    Calendars

    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
    @Named
    -0.08
     confused
    -0.08
    Settings
    -0.08
     thái
    -0.07
     깨
    -0.07
    Bound
    -0.07
     Kne
    -0.07
     configured
    -0.07
    Regional
    -0.07
     behaved
    -0.07
    POSITIVE LOGITS
     crypto
    0.08
    ecd
    0.08
     Umm
    0.07
     cyclone
    0.07
     Mp
    0.07
     dasar
    0.07
    onnen
    0.07
    月至
    0.07
     nom
    0.07
     mudah
    0.07
    Activations Density 0.001%

    No Known Activations