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. 98601
    Prev
    Next
    INDEX
    Explanations

    parentheses/slashes

    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
    Tk
    -0.08
     crédit
    -0.08
    EA
    -0.08
     ocean
    -0.08
     sleek
    -0.08
     která
    -0.07
     creme
    -0.07
     eye
    -0.07
     sun
    -0.07
     mistr
    -0.07
    POSITIVE LOGITS
    Bal
    0.09
     Bal
    0.08
    -Mar
    0.08
     boleh
    0.08
     Download
    0.08
     standings
    0.08
     മാര്
    0.07
    .mar
    0.07
    Mar
    0.07
    _category
    0.07
    Activations Density 0.000%

    No Known Activations