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. 19040
    Prev
    Next
    INDEX
    Explanations

    stopping, removing, pausing things

    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
     creativity
    -0.08
    టి
    -0.08
     쇼
    -0.07
     Creativity
    -0.07
    bein
    -0.07
     jacket
    -0.07
     একটু
    -0.07
    جع
    -0.07
    叫
    -0.07
     compre
    -0.07
    POSITIVE LOGITS
     aquellos
    0.13
     unsuitable
    0.13
     उन
    0.13
     those
    0.13
     aquellas
    0.12
     offending
    0.12
     unfavorable
    0.12
     problematic
    0.12
    jenigen
    0.12
    那些
    0.12
    Activations Density 0.016%

    No Known Activations