© 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. 69097
    Prev
    Next
    INDEX
    Explanations

    .h

    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
    用了
    -0.08
    piegel
    -0.08
     Dress
    -0.07
    idh
    -0.07
    پرد
    -0.07
     toku
    -0.07
     stigma
    -0.07
    κτη
    -0.07
    πο
    -0.07
    dress
    -0.07
    POSITIVE LOGITS
     самол
    0.09
     congen
    0.09
     �
    0.08
     lao
    0.08
    <Task
    0.08
    0.08
     സമയം
    0.08
    0.08
     tractors
    0.08
    [assembly
    0.08
    Activations Density 0.002%

    No Known Activations