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. 98155
    Prev
    Next
    INDEX
    Explanations

    UiPath and programming

    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
     Multif
    -0.10
     Punkten
    -0.08
     legislation
    -0.08
     pág
    -0.08
    ностях
    -0.08
     Mold
    -0.07
     Perkins
    -0.07
     Hubb
    -0.07
     Tabelle
    -0.07
     Platz
    -0.07
    POSITIVE LOGITS
    .activity
    0.08
     गतिविध
    0.08
     �
    0.08
     activity
    0.08
    .activities
    0.08
     starvation
    0.08
     package
    0.08
     variables
    0.08
     stitched
    0.08
    ウ
    0.08
    Activations Density 0.004%

    No Known Activations