© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64056
    Prev
    Next
    INDEX
    Explanations

    Sports score reduction

    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
     otim
    -0.08
    {:
    -0.08
    属性
    -0.08
    cation
    -0.07
     Basically
    -0.07
     Overseas
    -0.07
     কৃষ
    -0.07
     agrícola
    -0.07
     agricultura
    -0.07
     Decisions
    -0.07
    POSITIVE LOGITS
     comeback
    0.10
     earnest
    0.09
    Increase
    0.08
     pagkakata
    0.08
     मौका
    0.08
     versucht
    0.08
     gadgets
    0.08
    illow
    0.08
    0.08
     eks
    0.08
    Activations Density 0.047%
    No Known Activations