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. 76297
    Prev
    Next
    INDEX
    Explanations

    by

    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
    fires
    -0.08
    心得
    -0.08
     çalışan
    -0.08
     định
    -0.08
     coleta
    -0.07
     εργα
    -0.07
     leveraging
    -0.07
     kapsamında
    -0.07
     сотрудники
    -0.07
    )],↵
    -0.07
    POSITIVE LOGITS
     ersetzen
    0.10
     remplac
    0.10
     substitutions
    0.09
     substituted
    0.09
     reempl
    0.09
     замен
    0.09
    替
    0.09
     заменить
    0.09
     sustitu
    0.08
     vervangen
    0.08
    Activations Density 0.007%

    No Known Activations