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. 98437
    Prev
    Next
    INDEX
    Explanations

    m

    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
    睛
    -0.08
    phants
    -0.08
     elegance
    -0.08
    adies
    -0.08
     prochains
    -0.08
     ಆಗ
    -0.08
    elect
    -0.08
    ccions
    -0.08
    moder
    -0.08
    お願
    -0.07
    POSITIVE LOGITS
    2
    0.13
    3
    0.12
     xə
    0.11
    .к
    0.10
    "ר
    0.10
    ²
    0.10
    <
    0.09
    ২
    0.09
    QL
    0.09
    ৩
    0.09
    Activations Density 0.005%

    No Known Activations