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. 113834
    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
    "We
    -0.08
    _beta
    -0.08
    /Page
    -0.07
    _*
    -0.07
    (Op
    -0.07
    "h
    -0.07
     suggestion
    -0.07
    —that
    -0.07
    Ruby
    -0.07
    "|
    -0.07
    POSITIVE LOGITS
     celle
    0.08
     celui
    0.08
     野
    0.08
    ുസ്ത
    0.08
     ช่อง
    0.08
    stur
    0.08
     ジ
    0.08
     LOG
    0.08
    ुस
    0.08
     Rece
    0.07
    Activations Density 0.017%

    No Known Activations