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. 98291
    Prev
    Next
    INDEX
    Explanations

    .e

    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
    adero
    -0.07
     standar
    -0.06
     masterpiece
    -0.06
    }^{
    -0.06
    _User
    -0.06
     afl
    -0.06
    -0.06
    ायला
    -0.06
    -0.06
     Interpreter
    -0.06
    POSITIVE LOGITS
    inclusive
    0.10
    writers
    0.09
    teous
    0.09
    clusive
    0.09
     podia
    0.09
    باشد
    0.08
     Vorsitz
    0.08
    makers
    0.08
    .learn
    0.08
     дониш
    0.08
    Activations Density 0.000%

    No Known Activations