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. 98499
    Prev
    Next
    INDEX
    Explanations

    say two letter combinations

    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
     segu
    -0.11
     utilizz
    -0.10
     aiut
    -0.10
    imte
    -0.09
     offr
    -0.08
    uttur
    -0.08
     effettu
    -0.08
     mostr
    -0.08
    rezz
    -0.08
     aggiorn
    -0.07
    POSITIVE LOGITS
     richi
    0.15
     migliori
    0.14
     giochi
    0.11
     temi
    0.11
     lavi
    0.11
    uti
    0.10
     testi
    0.10
    āji
    0.10
    coli
    0.10
    illi
    0.10
    Activations Density 0.021%

    No Known Activations