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. 15-RESID-POST-AA
    6. 19086
    Prev
    Next
    INDEX
    Explanations

    Construct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     medicamentos
    -0.09
     medications
    -0.08
     girls
    -0.08
    644
    -0.08
    112
    -0.07
    163
    -0.07
    弃
    -0.07
    391
    -0.07
     crianças
    -0.07
     extingu
    -0.07
    POSITIVE LOGITS
    ात्मक
    0.12
    पूर्ण
    0.10
    wirit
    0.09
     विधायक
    0.09
     thoughtfully
    0.09
     witty
    0.09
     articulate
    0.09
    SMART
    0.09
    िक्त
    0.09
     тез
    0.09
    Activations Density 0.001%

    No Known Activations