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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98553
    Prev
    Next
    INDEX
    Explanations

    -

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -Friendly
    -0.10
     tecnológico
    -0.09
    -specific
    -0.09
     spéciale
    -0.09
    -exclusive
    -0.09
    -friendly
    -0.09
    -Compatible
    -0.09
     especiais
    -0.08
     especiales
    -0.08
    -Based
    -0.08
    POSITIVE LOGITS
     grade
    0.15
     ready
    0.15
    grade
    0.14
    Grade
    0.14
     Grade
    0.13
    Ready
    0.13
     readiness
    0.12
    ready
    0.12
    _grade
    0.12
     готов
    0.12
    Activations Density 0.006%

    No Known Activations