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. 98562
    Prev
    Next
    INDEX
    Explanations

    say "د" words

    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
     latte
    -0.09
     distinction
    -0.08
     laser
    -0.08
     brackets
    -0.08
    .ident
    -0.07
     IG
    -0.07
     pont
    -0.07
    ctor
    -0.07
    lict
    -0.07
     luas
    -0.07
    POSITIVE LOGITS
    د
    0.11
    مار
    0.08
    ิม
    0.08
    arela
    0.08
     د
    0.08
    نى
    0.07
    Chimp
    0.07
    -Men
    0.07
    bir
    0.07
     ஓ
    0.07
    Activations Density 0.000%

    No Known Activations