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. 77220
    Prev
    Next
    INDEX
    Explanations

    foreign languages and "Great"

    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
    yeah
    -0.09
     sko
    -0.09
    fers
    -0.08
     पूरी
    -0.08
     respite
    -0.08
     entice
    -0.07
    ferred
    -0.07
    stip
    -0.07
    prep
    -0.07
    atore
    -0.07
    POSITIVE LOGITS
    -scale
    0.10
     vast
    0.08
     highways
    0.08
    ใหญ่
    0.08
     magnificent
    0.08
     शक्त
    0.08
     leid
    0.08
     grandeur
    0.08
    -grand
    0.08
     кня
    0.08
    Activations Density 0.031%

    No Known Activations