© 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. 18674
    Prev
    Next
    INDEX
    Explanations

    Math/logic equations

    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
     ebenfalls
    -0.09
    —and
    -0.08
     والتعليم
    -0.08
     justement
    -0.08
    .).
    -0.08
     funk
    -0.07
    -0.07
    也是
    -0.07
    :↵//↵//
    -0.07
     utilisent
    -0.07
    POSITIVE LOGITS
     ✓
    0.11
    هذا
    0.10
     هذا
    0.09
     questo
    0.09
     ==>
    0.09
     हा
    0.09
     concludes
    0.08
     =>
    0.08
     satisfies
    0.08
     ✅
    0.08
    Activations Density 0.053%
    No Known Activations