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. 11-RESID-POST-AA
    6. 88288
    Prev
    Next
    INDEX
    Explanations

    Logarithm math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Massage
    -0.09
     лиц
    -0.08
     OAuth
    -0.08
    /npm
    -0.07
    ullet
    -0.07
    细
    -0.07
     MPO
    -0.07
     scour
    -0.07
     colch
    -0.07
    emos
    -0.07
    POSITIVE LOGITS
     레
    0.08
     experimentally
    0.08
     ชั้น
    0.07
     ವರ್�
    0.07
     aufgrund
    0.07
     Apprentice
    0.07
     года
    0.07
     秒
    0.07
     compartment
    0.07
    altura
    0.07
    Activations Density 0.022%

    No Known Activations