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. 98379
    Prev
    Next
    INDEX
    Explanations

    Regional dishes

    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
    itled
    -0.08
     kaga
    -0.08
     llevo
    -0.08
    ENTRY
    -0.08
    &oacute
    -0.08
    .ta
    -0.08
     Senator
    -0.08
    oraj
    -0.08
    orique
    -0.08
     desped
    -0.08
    POSITIVE LOGITS
    Lamp
    0.09
    mate
    0.08
     matcher
    0.08
    Pho
    0.08
    Matcher
    0.08
    Binder
    0.08
    men
    0.08
    are
    0.08
     italien
    0.08
    Cass
    0.08
    Activations Density 0.002%

    No Known Activations