Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 102967
    Prev
    Next
    INDEX
    Explanations

    Props

    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
     (£
    -0.08
     coin
    -0.07
     recherch
    -0.07
    饭
    -0.07
     apprend
    -0.07
     MSc
    -0.07
     aprendiz
    -0.07
     %.
    -0.07
     الميز
    -0.07
    ysg
    -0.07
    POSITIVE LOGITS
    (cons
    0.08
     шта
    0.08
    ()
    ↵
    ↵
    0.08
     ()
    ↵
    0.08
    τύ
    0.08
     urlpatterns
    0.08
     cosa
    0.08
     declara
    0.07
    ('[
    0.07
     фору
    0.07
    Activations Density 0.001%

    No Known Activations