© 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. 22581
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     वालों
    -0.10
     주변
    -0.09
     neighboring
    -0.09
     feminino
    -0.09
     nearby
    -0.09
     surrounding
    -0.08
     strangers
    -0.08
     Nearby
    -0.08
    umers
    -0.08
    target
    -0.08
    POSITIVE LOGITS
    (op
    0.09
     fotografías
    0.09
    opo
    0.09
     opp
    0.09
    'op
    0.09
    op
    0.08
     opos
    0.08
    .op
    0.08
    	op
    0.08
     OP
    0.08
    Activations Density 0.001%

    No Known Activations