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. 118
    Prev
    Next
    INDEX
    Explanations

    Research/journal context

    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
    %以上
    -0.08
    nton
    -0.08
    krut
    -0.08
    %</
    -0.08
    mäßig
    -0.08
    Tensor
    -0.08
     relatief
    -0.07
    Engine
    -0.07
     ongeveer
    -0.07
    .Chrome
    -0.07
    POSITIVE LOGITS
     debris
    0.08
    附
    0.08
     coating
    0.07
    +x
    0.07
     bundle
    0.07
     gallery
    0.07
     میر
    0.07
     kontinuier
    0.07
     கலந்து
    0.07
     collectif
    0.07
    Activations Density 0.002%

    No Known Activations