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. 15-RESID-POST-AA
    6. 148
    Prev
    Next
    INDEX
    Explanations

    tax

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tup
    -0.09
    -memory
    -0.09
     warrior
    -0.08
     memoir
    -0.08
     bipolar
    -0.08
     Corpus
    -0.08
    tun
    -0.08
     Chronicles
    -0.08
     வீர
    -0.08
    .Player
    -0.08
    POSITIVE LOGITS
     taxes
    0.16
     taxe
    0.14
    税
    0.13
    Taxes
    0.13
     government
    0.12
    VAT
    0.12
     taxable
    0.12
     VAT
    0.12
     tax
    0.12
    税込
    0.12
    Activations Density 0.018%

    No Known Activations