Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 48433
    Prev
    Next
    INDEX
    Explanations

    Hyundai

    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
    韓
    -0.11
     korea
    -0.11
    韩国
    -0.11
     Kazakhstan
    -0.10
     Korea
    -0.10
     kore
    -0.10
     Korean
    -0.10
     Kore
    -0.10
     korean
    -0.09
     Keh
    -0.09
    POSITIVE LOGITS
     Electric
    0.10
     Electronics
    0.09
     BBQ
    0.09
    .util
    0.09
     Wave
    0.08
    -electric
    0.08
    Electric
    0.08
     automobiles
    0.08
     ਦਿੱ
    0.08
    Wave
    0.08
    Activations Density 0.009%

    No Known Activations