© 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. 68271
    Prev
    Next
    INDEX
    Explanations

    coffee

    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
    ాయి
    -0.08
    ‌ని
    -0.08
     eus
    -0.08
     Census
    -0.08
    లేదు
    -0.08
    .^
    -0.08
     Daly
    -0.08
     Decreto
    -0.08
    Adult
    -0.07
    ,etc
    -0.07
    POSITIVE LOGITS
    _nt
    0.08
    0.08
     llev
    0.08
    ptide
    0.08
    aaa
    0.08
     nano
    0.08
    ferð
    0.08
    ק
    0.07
    epy
    0.07
    jar
    0.07
    Activations Density 0.003%
    No Known Activations