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. 58437
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     থাকতে
    -0.08
     অন্য
    -0.08
    */↵↵↵
    -0.08
    Ber
    -0.08
     কি
    -0.07
     মানুষ
    -0.07
     teenager
    -0.07
     উ
    -0.07
     অনুভ
    -0.07
     বদ
    -0.07
    POSITIVE LOGITS
     ශ
    0.08
     cierre
    0.08
    振
    0.08
    ේශ
    0.08
     phosphorylation
    0.08
     уж
    0.08
     verður
    0.08
    ämme
    0.08
     Marun
    0.08
     initialise
    0.08
    Activations Density 0.065%

    No Known Activations