© 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. 54765
    Prev
    Next
    INDEX
    Explanations

    Commons

    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
     developmental
    -0.09
    Projected
    -0.09
    هما
    -0.08
     الأور
    -0.08
    indest
    -0.08
     cerebral
    -0.07
    ตอน
    -0.07
     projections
    -0.07
    Synchronization
    -0.07
    bibigay
    -0.07
    POSITIVE LOGITS
     taak
    0.08
    .hover
    0.08
     karya
    0.08
     wget
    0.08
     peri
    0.07
     patrim
    0.07
    .commons
    0.07
    .is
    0.07
     aru
    0.07
     tenancy
    0.07
    Activations Density 0.001%

    No Known Activations