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. 117
    Prev
    Next
    INDEX
    Explanations

    const

    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
    awaiter
    -0.08
    Fun
    -0.08
    ;c
    -0.08
    .printf
    -0.08
    fun
    -0.08
    -gl
    -0.08
    FUN
    -0.08
    (patient
    -0.08
    werkt
    -0.08
    GL
    -0.07
    POSITIVE LOGITS
    _REFRESH
    0.08
     mune
    0.08
     Merkel
    0.08
    ">';↵
    0.08
     relinqu
    0.07
     khí
    0.07
     kholo
    0.07
    _MISC
    0.07
     gist
    0.07
     milk
    0.07
    Activations Density 0.005%

    No Known Activations