© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18897
    Prev
    Next
    INDEX
    Explanations

    reflect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ophyll
    -0.10
    תגובות
    -0.09
    යක
    -0.08
    issimi
    -0.08
     razem
    -0.08
    යක්
    -0.08
     reactie
    -0.08
     wraz
    -0.08
    ży
    -0.08
     koos
    -0.07
    POSITIVE LOGITS
    ively
    0.13
    ive
    0.12
     accurately
    0.11
    ivity
    0.11
     realities
    0.10
    iveness
    0.10
     on
    0.10
    准确
    0.10
     reality
    0.10
     asupra
    0.10
    Activations Density 0.010%

    No Known Activations