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. 65477
    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
    触
    -0.09
     kolej
    -0.08
    观点
    -0.07
     lyn
    -0.07
    ysis
    -0.07
     Que
    -0.07
    reo
    -0.07
     जाए
    -0.07
     společ
    -0.07
     mung
    -0.07
    POSITIVE LOGITS
    Farm
    0.08
    مز
    0.08
     Moreover
    0.08
    cour
    0.07
     এছ
    0.07
     nanot
    0.07
     compre
    0.07
    故
    0.07
     residente
    0.07
    ended
    0.07
    Activations Density 0.076%

    No Known Activations