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. 77521
    Prev
    Next
    INDEX
    Explanations

    Countries

    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
     مشکل
    -0.09
     feas
    -0.08
     Ple
    -0.08
     saira
    -0.08
    ewel
    -0.08
     Constraint
    -0.08
     kuinka
    -0.08
     Stream
    -0.08
     staffs
    -0.08
    =start
    -0.08
    POSITIVE LOGITS
     अमेरिका
    0.13
     China
    0.12
     المتحدة
    0.12
    China
    0.12
     দেশে
    0.12
     અમેર
    0.11
     Canada
    0.11
    Canada
    0.11
    Australia
    0.11
    国外
    0.10
    Activations Density 0.035%

    No Known Activations