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. 98136
    Prev
    Next
    INDEX
    Explanations

    say "olitan"

    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
    ímp
    -0.10
    ésus
    -0.10
    éasáin
    -0.09
     �
    -0.09
    Ак
    -0.09
    	text
    -0.09
    Им
    -0.09
    .text
    -0.09
    Мон
    -0.09
    (text
    -0.09
    POSITIVE LOGITS
    .pages
    0.09
     artistic
    0.08
    olitan
    0.08
    .page
    0.08
    .rs
    0.07
    studio
    0.07
    .mall
    0.07
     stud
    0.07
    才能
    0.07
     a
    0.07
    Activations Density 0.001%

    No Known Activations