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. 23-RESID-POST-AA
    6. 98236
    Prev
    Next
    INDEX
    Explanations

    st

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ailing
    -0.09
     توانید
    -0.08
    ‌توانید
    -0.08
     poised
    -0.08
     mastering
    -0.08
     datings
    -0.08
     faulty
    -0.08
     hoeven
    -0.08
     lowering
    -0.08
     knocking
    -0.08
    POSITIVE LOGITS
    ifle
    0.14
    ymy
    0.09
     Pentec
    0.08
    xis
    0.07
    sep
    0.07
    oke
    0.07
    unts
    0.07
    NAV
    0.07
    sworth
    0.07
     arcs
    0.07
    Activations Density 0.000%

    No Known Activations