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. 9118
    Prev
    Next
    INDEX
    Explanations

    Formulaic prompts

    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
    יטות
    -0.09
     усп
    -0.08
    arrer
    -0.08
    ائص
    -0.07
    alla
    -0.07
     арх
    -0.07
     για
    -0.07
     succeeds
    -0.07
    صال
    -0.07
    =find
    -0.07
    POSITIVE LOGITS
    elha
    0.08
     Ambos
    0.08
    uidado
    0.08
     Doch
    0.08
     wirst
    0.07
     Pasc
    0.07
     neemt
    0.07
     spacing
    0.07
     Atualmente
    0.07
    दो
    0.07
    Activations Density 0.003%

    No Known Activations