© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6039
    Prev
    Next
    INDEX
    Explanations

    Locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Khmer
    -0.09
     Malaysian
    -0.09
     Indonesian
    -0.09
     Burmese
    -0.09
     Malayalam
    -0.09
     Bruno
    -0.08
     Malaysia
    -0.08
     Bengali
    -0.08
     Barang
    -0.08
    ้า
    -0.08
    POSITIVE LOGITS
     Solo
    0.11
     Y
    0.10
    Band
    0.10
    band
    0.09
     cire
    0.09
    че
    0.09
     Cil
    0.08
    Solo
    0.08
    Y
    0.08
     Sle
    0.08
    Activations Density 0.003%

    No Known Activations