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. 19199
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning

    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
    �
    -0.08
    \xe
    -0.08
     Pico
    -0.08
    -output
    -0.08
    -clear
    -0.07
    annen
    -0.07
    -resource
    -0.07
    �ოფ
    -0.07
    \xd
    -0.07
    -pl
    -0.07
    POSITIVE LOGITS
    ''.
    0.08
    hez
    0.08
     માર
    0.08
    二
    0.08
     physique
    0.08
     fis
    0.08
    zky
    0.08
    �
    0.08
     фіз
    0.07
    Than
    0.07
    Activations Density 0.025%

    No Known Activations