© 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. 717
    Prev
    Next
    INDEX
    Explanations

    vector embedding

    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
     Loose
    -0.09
     даму
    -0.08
     teş
    -0.08
     etmek
    -0.08
     dopu
    -0.08
     Nether
    -0.08
    (Resources
    -0.08
    ‌ప
    -0.07
     drought
    -0.07
     pete
    -0.07
    POSITIVE LOGITS
     stored
    0.08
     spam
    0.07
    .tolist
    0.07
     voicemail
    0.07
     Malayalam
    0.07
     whales
    0.07
    Fns
    0.07
     sinó
    0.07
     volumes
    0.07
     Stimme
    0.07
    Activations Density 0.002%

    No Known Activations