© 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. 11-RESID-POST-AA
    11. 26561
    Prev
    Next
    INDEX
    Explanations

    geometry

    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
     official
    -0.08
    _markup
    -0.08
     sugary
    -0.08
    ขาย
    -0.07
     runoff
    -0.07
     населения
    -0.07
    ค่
    -0.07
     barter
    -0.07
    Crunch
    -0.07
     balancing
    -0.07
    POSITIVE LOGITS
    所属
    0.08
     relation
    0.08
    _relation
    0.08
    فرنس
    0.08
     leash
    0.08
    ‌ట
    0.08
     ఇప్పటికే
    0.08
    之间
    0.08
    ‌కు
    0.08
     Relation
    0.08
    Activations Density 0.027%

    No Known Activations