Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11736
    Prev
    Next
    INDEX
    Explanations

    the

    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
     tuner
    -0.09
     trig
    -0.09
     instituciones
    -0.08
     Körper
    -0.08
     iconic
    -0.08
    Trig
    -0.08
     शरीर
    -0.08
     körper
    -0.08
     straf
    -0.08
     institución
    -0.08
    POSITIVE LOGITS
    Deadline
    0.11
     پروژه
    0.11
     Deadline
    0.11
     проектов
    0.11
    deadline
    0.11
     коллег
    0.11
     colleague
    0.11
     stakeholders
    0.11
     deadlines
    0.11
     colleagues
    0.11
    Activations Density 0.074%

    No Known Activations