© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 523
    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
     tribal
    -0.08
    ADA
    -0.08
     вероят
    -0.08
    ویی
    -0.07
    tria
    -0.07
     Tribal
    -0.07
     runtime
    -0.07
    -0.07
    -paper
    -0.07
     Dental
    -0.07
    POSITIVE LOGITS
    مل
    0.09
    mə
    0.08
    gay
    0.08
    nw
    0.07
     Luciano
    0.07
     لقاء
    0.07
     bargain
    0.07
    lags
    0.07
     misery
    0.07
    歩
    0.07
    Activations Density 0.012%
    No Known Activations