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. 45834
    Prev
    Next
    INDEX
    Explanations

    true positive rate

    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
    瓶
    -0.08
     stitch
    -0.07
    �
    -0.07
     renovation
    -0.07
    ounced
    -0.07
     prune
    -0.07
     cauza
    -0.07
    -feature
    -0.07
    uhl
    -0.07
    merge
    -0.07
    POSITIVE LOGITS
     uite
    0.08
     Gunn
    0.08
     ROC
    0.07
     نیم
    0.07
    edza
    0.07
     hvernig
    0.07
    როგ
    0.07
    واک
    0.07
     necə
    0.07
     Αυ
    0.07
    Activations Density 0.001%

    No Known Activations