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. 98446
    Prev
    Next
    INDEX
    Explanations

    say "第一"

    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
    _single
    -0.08
    594
    -0.08
    "_
    -0.08
    _SINGLE
    -0.08
    textfield
    -0.08
    .inspect
    -0.07
    _STANDARD
    -0.07
    .client
    -0.07
    _TWO
    -0.07
     careless
    -0.07
    POSITIVE LOGITS
    目录
    0.18
     I
    0.14
    关键词
    0.14
     Introduction
    0.12
     Contents
    0.12
     keywords
    0.12
    目
    0.11
    Contents
    0.11
     Fore
    0.11
     Inhalts
    0.11
    Activations Density 0.022%

    No Known Activations