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. 65688
    Prev
    Next
    INDEX
    Explanations

    Exotic locations and trade

    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
     approach
    -0.08
     COPD
    -0.07
     kinetics
    -0.07
     सहभाग
    -0.07
     dynamics
    -0.07
     silencio
    -0.07
     Approach
    -0.07
     solving
    -0.07
     Oakland
    -0.07
     issue
    -0.07
    POSITIVE LOGITS
     exotic
    0.12
    东方
    0.11
     wond
    0.11
     exot
    0.11
     étrangères
    0.10
     بلاد
    0.10
     Europeans
    0.10
     विदेशी
    0.10
     Exotic
    0.10
     étrang
    0.09
    Activations Density 0.026%

    No Known Activations