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. 45641
    Prev
    Next
    INDEX
    Explanations

    -

    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
     sofistic
    -0.08
     prer
    -0.08
     sophisticated
    -0.08
    ári
    -0.08
     ido
    -0.08
    -redux
    -0.07
    Shaders
    -0.07
     amo
    -0.07
    ienti
    -0.07
    श
    -0.07
    POSITIVE LOGITS
    usion
    0.09
     قطاع
    0.08
     عج
    0.08
    0.08
     القطاع
    0.08
     ciddi
    0.08
     البرنامج
    0.08
    itäten
    0.08
    ifying
    0.08
     அதை
    0.07
    Activations Density 0.013%

    No Known Activations