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. 19389
    Prev
    Next
    INDEX
    Explanations

    Creating directories

    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
     mencionar
    -0.08
     l
    -0.08
     spies
    -0.07
    ami
    -0.07
    -0.07
     this
    -0.07
    -0.07
    ın
    -0.07
     critical
    -0.07
     coinvol
    -0.07
    POSITIVE LOGITS
     rarement
    0.10
     rarely
    0.10
     редко
    0.09
     экономики
    0.09
     overlapping
    0.09
     seldom
    0.09
     Occasionally
    0.08
     nooit
    0.08
     tolerate
    0.08
     неаб
    0.08
    Activations Density 0.002%

    No Known Activations