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. 130917
    Prev
    Next
    INDEX
    Explanations

    say "da" ending

    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
     গভ
    -0.07
     ডিস
    -0.07
     plum
    -0.07
    (hash
    -0.07
     discourage
    -0.07
     Tuna
    -0.07
     আটক
    -0.07
    .hash
    -0.07
    313
    -0.07
     বিশ্বাস
    -0.07
    POSITIVE LOGITS
    alay
    0.08
     kənd
    0.08
    acional
    0.08
    ac
    0.08
    acaq
    0.08
    ुख
    0.08
     subt
    0.07
    UPPORT
    0.07
    masına
    0.07
     lyn
    0.07
    Activations Density 0.000%

    No Known Activations