© 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. 99260
    Prev
    Next
    INDEX
    Explanations

    math/Ceva's theorem

    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
     pension
    -0.08
     Constructor
    -0.08
    养老金
    -0.07
     forecast
    -0.07
    بي
    -0.07
    883
    -0.07
     forecasts
    -0.07
    Destructor
    -0.07
     Treasury
    -0.07
     constructors
    -0.07
    POSITIVE LOGITS
     ratios
    0.09
     clockwise
    0.09
    _Control
    0.08
     uterus
    0.08
    ratio
    0.08
    _ratio
    0.08
     Ratio
    0.08
     krv
    0.07
     Political
    0.07
     mundial
    0.07
    Activations Density 0.006%

    No Known Activations