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. 42145
    Prev
    Next
    INDEX
    Explanations

    pioneer

    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
    อด
    -0.09
     Tach
    -0.09
     Derm
    -0.08
    બ
    -0.08
     aigu
    -0.08
     Aal
    -0.08
    రు
    -0.07
    พัก
    -0.07
     Я
    -0.07
     Klang
    -0.07
    POSITIVE LOGITS
     pioneering
    0.08
     בתחום
    0.08
     groundwork
    0.07
    leda
    0.07
     pione
    0.07
     breakthroughs
    0.07
     geological
    0.07
    Medical
    0.07
     medical
    0.07
     cer
    0.07
    Activations Density 0.011%

    No Known Activations