© 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. 108811
    Prev
    Next
    INDEX
    Explanations

    o

    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
     regiment
    -0.09
    imentation
    -0.08
    .so
    -0.08
     gond
    -0.08
     teamwork
    -0.07
    .poll
    -0.07
     altitude
    -0.07
     tactical
    -0.07
     വിമ
    -0.07
     stimulation
    -0.07
    POSITIVE LOGITS
     Beach
    0.08
     dibuat
    0.08
     eggs
    0.08
     entidade
    0.07
    ેમ્બ
    0.07
     entidades
    0.07
     carving
    0.07
    �
    0.07
     Kosten
    0.07
     Dafür
    0.07
    Activations Density 0.001%

    No Known Activations