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. 19104
    Prev
    Next
    INDEX
    Explanations

    crash

    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
     mastery
    -0.08
     marketing
    -0.08
     sensual
    -0.08
     algodón
    -0.08
     inscription
    -0.08
     sobr
    -0.08
     linkedin
    -0.08
     Wilaya
    -0.08
     longing
    -0.08
     scent
    -0.08
    POSITIVE LOGITS
     crashes
    0.20
     crash
    0.18
     crashing
    0.15
     crashed
    0.15
     Crash
    0.15
    Crash
    0.14
    �
    0.12
     �
    0.12
     meltdown
    0.12
     fatal
    0.12
    Activations Density 0.012%

    No Known Activations