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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 111565
    Prev
    Next
    INDEX
    Explanations

    redistributed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gezond
    -0.09
     स्वस्थ
    -0.09
     healthy
    -0.08
    posito
    -0.08
    ювання
    -0.08
     gezonde
    -0.08
    benza
    -0.08
     zdrav
    -0.08
     catal
    -0.07
    usebenza
    -0.07
    POSITIVE LOGITS
     неб
    0.08
    rias
    0.08
    ்ர
    0.08
    发表评论
    0.07
     страницу
    0.07
    рид
    0.07
    -bottom
    0.07
    лев
    0.07
     Urteil
    0.07
     leopard
    0.07
    Activations Density 0.003%

    No Known Activations