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. 98081
    Prev
    Next
    INDEX
    Explanations

    Different 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
    ויפ
    -0.09
    ័ត
    -0.08
    ويض
    -0.08
    endere
    -0.08
     brand
    -0.08
     �
    -0.07
     truc
    -0.07
    alata
    -0.07
    alla
    -0.07
    uyla
    -0.07
    POSITIVE LOGITS
    :Is
    0.08
    Tags
    0.07
    ceb
    0.07
    Find
    0.07
    :int
    0.07
     claro
    0.07
    .is
    0.07
    .tags
    0.07
    /The
    0.07
    :Set
    0.07
    Activations Density 0.001%

    No Known Activations