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. 58847
    Prev
    Next
    INDEX
    Explanations

    Code-related text

    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
     تس
    -0.08
     governmental
    -0.08
     philanthropic
    -0.08
    endif
    -0.08
    EOS
    -0.08
    otiate
    -0.08
     concess
    -0.08
    加盟
    -0.08
     ಗುರು
    -0.07
    内部
    -0.07
    POSITIVE LOGITS
     Alternative
    0.09
     assur
    0.09
     minecraft
    0.09
     avoidance
    0.09
     honn
    0.09
     approche
    0.09
    Alternative
    0.09
     zahr
    0.08
     indie
    0.08
     evitare
    0.08
    Activations Density 0.001%

    No Known Activations