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. 98414
    Prev
    Next
    INDEX
    Explanations

    say "rier"

    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
    Mixed
    -0.08
    Emergency
    -0.08
    ылы
    -0.08
    Busy
    -0.08
    More
    -0.08
     melts
    -0.08
    José
    -0.08
    Higher
    -0.08
    ers
    -0.08
     Smaller
    -0.08
    POSITIVE LOGITS
    rier
    0.09
    ukul
    0.08
    uller
    0.08
     hannu
    0.07
     Capp
    0.07
     Iglesias
    0.07
    -Life
    0.07
     Landschaft
    0.07
    ri
    0.07
     februari
    0.07
    Activations Density 0.000%

    No Known Activations