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. 98031
    Prev
    Next
    INDEX
    Explanations

    Numerical calculations

    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
    oops
    -0.08
     naast
    -0.08
    SUP
    -0.08
     suplement
    -0.08
     supplemental
    -0.08
    _bbox
    -0.07
     jā
    -0.07
    ်
    -0.07
     ј
    -0.07
     webcam
    -0.07
    POSITIVE LOGITS
    408
    0.08
    .exchange
    0.08
    oration
    0.08
    280
    0.08
     Hooks
    0.07
     prostitute
    0.07
    uerda
    0.07
    792
    0.07
    ागत
    0.07
    .live
    0.07
    Activations Density 0.002%

    No Known Activations