© 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. 26497
    Prev
    Next
    INDEX
    Explanations

    point

    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
     upe
    -0.09
    ្ទ
    -0.09
    ↵		
↵
    -0.08
     technological
    -0.08
     grammatical
    -0.08
     restructuring
    -0.08
     agenda
    -0.08
     surplus
    -0.08
     agendas
    -0.08
     assurance
    -0.07
    POSITIVE LOGITS
    则
    0.09
    )obj
    0.08
     therein
    0.08
    OBS
    0.08
     subdiv
    0.07
     创建
    0.07
     Nis
    0.07
     MAX
    0.07
    (observer
    0.07
    Î
    0.07
    Activations Density 0.050%

    No Known Activations