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. 49703
    Prev
    Next
    INDEX
    Explanations

    _k

    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
     पोख
    -0.08
    宝
    -0.08
    oonni
    -0.08
    otherapeut
    -0.08
     anniversary
    -0.07
     宝
    -0.07
    墓
    -0.07
    Health
    -0.07
    -war
    -0.07
    Heal
    -0.07
    POSITIVE LOGITS
     Sac
    0.07
    .Swing
    0.07
     theorem
    0.07
    اع
    0.07
     melalui
    0.07
    .activation
    0.07
     Microsoft's
    0.07
    .micro
    0.07
     Veja
    0.07
     tuned
    0.07
    Activations Density 0.003%

    No Known Activations