© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 65355
    Prev
    Next
    INDEX
    Explanations

    tagging

    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
     servizi
    -0.08
     Industr
    -0.08
     servicios
    -0.08
     Serviços
    -0.08
     Servicios
    -0.08
     Services
    -0.08
    erializer
    -0.08
    ervices
    -0.07
     strstr
    -0.07
    ynth
    -0.07
    POSITIVE LOGITS
     первонач
    0.09
     jarenlang
    0.08
     ஆண்டு
    0.08
     permanently
    0.08
     marking
    0.08
     монитор
    0.08
     최초
    0.08
     WAV
    0.08
    GPS
    0.08
     implanted
    0.08
    Activations Density 0.001%

    No Known Activations