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. 53271
    Prev
    Next
    INDEX
    Explanations

    Recall and Sensitivity

    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
     تشير
    -0.08
     Ken
    -0.08
    -0.08
     напряж
    -0.08
     przeci
    -0.08
    -0.08
     நாள்
    -0.08
    -0.08
     dress
    -0.07
    ***↵
    -0.07
    POSITIVE LOGITS
     missed
    0.14
    遗漏
    0.13
     обнаруж
    0.11
     Coverage
    0.11
     ચૂ
    0.10
     Detection
    0.10
    漏
    0.10
    Detection
    0.10
     dete
    0.10
    Coverage
    0.10
    Activations Density 0.013%

    No Known Activations