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. 15-RESID-POST-AA
    6. 19200
    Prev
    Next
    INDEX
    Explanations

    say "/s or /h"

    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
    schap
    -0.09
     mnoho
    -0.09
    媳
    -0.09
    yş
    -0.08
    ântico
    -0.08
     μεγάλη
    -0.08
     chemically
    -0.08
     आसपास
    -0.08
     тему
    -0.08
     trecho
    -0.08
    POSITIVE LOGITS
     per
    0.09
     për
    0.08
     Percentage
    0.08
     प्रति
    0.08
    Per
    0.08
    _percentage
    0.08
    _per
    0.08
     volts
    0.08
    Percentage
    0.08
    Rate
    0.07
    Activations Density 0.012%

    No Known Activations