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. 131060
    Prev
    Next
    INDEX
    Explanations

    clar

    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
    ization
    -0.09
    izers
    -0.08
    661
    -0.08
    ale
    -0.08
    але
    -0.08
    isers
    -0.07
    isation
    -0.07
     collaborating
    -0.07
    igion
    -0.07
     options
    -0.07
    POSITIVE LOGITS
    ifies
    0.13
    ifiée
    0.09
    ioned
    0.09
     говорится
    0.09
    istically
    0.09
    antically
    0.09
    inarily
    0.09
    ifying
    0.09
    ifiés
    0.08
    ifiées
    0.08
    Activations Density 0.003%

    No Known Activations