© 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. 11-RESID-POST-AA
    11. 70466
    Prev
    Next
    INDEX
    Explanations

    fitness

    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
     uml
    -0.09
     métallique
    -0.08
    נו
    -0.08
    键
    -0.08
     metá
    -0.07
     Metadata
    -0.07
    _io
    -0.07
    漏洞
    -0.07
     Анал
    -0.07
     Jungen
    -0.07
    POSITIVE LOGITS
     beginners
    0.12
     beginner
    0.11
    初心
    0.10
     anyone
    0.10
     sedent
    0.10
    Everyone
    0.10
    Anyone
    0.09
     शुरुआ
    0.09
     indoors
    0.08
     pregnant
    0.08
    Activations Density 0.024%

    No Known Activations