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. 19137
    Prev
    Next
    INDEX
    Explanations

    exaggerated

    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
     NICE
    -0.08
     feuilles
    -0.08
    .uid
    -0.08
    uid
    -0.08
     chatte
    -0.08
    initi
    -0.07
     chatted
    -0.07
     endlich
    -0.07
    Lunch
    -0.07
     texte
    -0.07
    POSITIVE LOGITS
     exaggerated
    0.24
     exagger
    0.22
     exager
    0.19
     caric
    0.15
     inflated
    0.12
     dramat
    0.12
     grotes
    0.12
     dramatic
    0.12
     stereotypes
    0.11
     enlarged
    0.11
    Activations Density 0.012%

    No Known Activations