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. 75137
    Prev
    Next
    INDEX
    Explanations

    Sugars

    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
     ...↵↵↵
    -0.07
    );
    ↵
    ↵
    ↵
    -0.07
     moderate
    -0.07
     Juni
    -0.07
     targeting
    -0.07
     oc
    -0.07
     "");↵↵
    -0.07
     overriding
    -0.06
     strategies
    -0.06
     Oc
    -0.06
    POSITIVE LOGITS
     myth
    0.10
     mythical
    0.09
    analytics
    0.08
     mythology
    0.08
    alleled
    0.08
    .analytics
    0.08
     выращ
    0.08
     wired
    0.08
    sembling
    0.08
     Katherine
    0.07
    Activations Density 0.001%

    No Known Activations