© 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. 69217
    Prev
    Next
    INDEX
    Explanations

    describing processes and rules

    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
    Earn
    -0.08
    Session
    -0.08
    Heading
    -0.08
    Visitor
    -0.07
    Potential
    -0.07
    Artifact
    -0.07
    Camp
    -0.07
    Downloaded
    -0.07
    Ashley
    -0.07
    asib
    -0.07
    POSITIVE LOGITS
     обнов
    0.11
    更新
    0.11
     reempl
    0.10
     업데이트
    0.10
     замен
    0.10
    替
    0.10
     ersetzt
    0.10
     ersetzen
    0.09
     gedeelt
    0.09
    刷新
    0.09
    Activations Density 0.006%

    No Known Activations