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. 44968
    Prev
    Next
    INDEX
    Explanations

    differences

    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
     integrity
    -0.07
    ARAM
    -0.07
     professors
    -0.07
    仪
    -0.07
     biomarkers
    -0.06
     researcher
    -0.06
    raz
    -0.06
     civil
    -0.06
     Dias
    -0.06
     <
    -0.06
    POSITIVE LOGITS
    екте
    0.09
     обществ
    0.08
     الكهرب
    0.08
     Меж
    0.08
    ials
    0.08
     interstate
    0.08
    ولد
    0.08
     cerita
    0.08
     avait
    0.08
    Passwords
    0.08
    Activations Density 0.015%

    No Known Activations