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. 78578
    Prev
    Next
    INDEX
    Explanations

    Currency appreciation/strength

    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
     Reservations
    -0.08
     Most
    -0.07
     Lieb
    -0.07
    :"
    -0.07
    ubes
    -0.07
     سلام
    -0.07
     Tiere
    -0.07
     Albums
    -0.07
     For
    -0.07
     Kategorie
    -0.07
    POSITIVE LOGITS
     выгод
    0.10
     strengthening
    0.09
     competitiveness
    0.09
    加强
    0.09
     укреп
    0.09
     strengthens
    0.09
     bargaining
    0.09
     strengthened
    0.09
    Negoti
    0.09
     усил
    0.09
    Activations Density 0.012%

    No Known Activations