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. 130724
    Prev
    Next
    INDEX
    Explanations

    say "utches"

    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
    ungan
    -0.08
    ensin
    -0.08
     ens
    -0.08
    erran
    -0.08
    -0.07
     egentlig
    -0.07
    lekile
    -0.07
     seit
    -0.07
     unfold
    -0.07
     amp
    -0.07
    POSITIVE LOGITS
    utches
    0.13
    utch
    0.11
    akan
    0.09
    aniu
    0.09
    λύ
    0.09
    Christ
    0.09
    ani
    0.08
    icos
    0.08
     Steen
    0.08
    Retries
    0.08
    Activations Density 0.001%

    No Known Activations