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. 130795
    Prev
    Next
    INDEX
    Explanations

    Bot responses in other languages

    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
    _package
    -0.09
     package
    -0.09
    _checkbox
    -0.08
    .package
    -0.08
    PACKAGE
    -0.07
    ções
    -0.07
     fan
    -0.07
     Package
    -0.07
     peny
    -0.07
     benod
    -0.07
    POSITIVE LOGITS
    STM
    0.09
     auxquels
    0.09
     Lumia
    0.08
     eut
    0.08
    LG
    0.08
    asn
    0.08
     auxqu
    0.08
     stockholm
    0.08
    dup
    0.08
    ILY
    0.08
    Activations Density 0.001%

    No Known Activations