© 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. 63973
    Prev
    Next
    INDEX
    Explanations

    courtyard

    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
     jet
    -0.09
     Lift
    -0.08
     dà
    -0.08
     gros
    -0.08
     jets
    -0.07
     lift
    -0.07
     fame
    -0.07
    $d
    -0.07
     Gord
    -0.07
     göz
    -0.07
    POSITIVE LOGITS
     courtyard
    0.10
    tyard
    0.08
    भूम
    0.08
     perimeter
    0.08
     plaza
    0.08
    sqm
    0.08
     Tomorrow
    0.07
     commun
    0.07
     alc
    0.07
    भाग
    0.07
    Activations Density 0.012%

    No Known Activations