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. 111617
    Prev
    Next
    INDEX
    Explanations

    French assistant chatbot

    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
    ayout
    -0.08
    -0.07
     odm
    -0.07
    迅
    -0.07
    .Res
    -0.07
    Dn
    -0.07
    験
    -0.07
    lossene
    -0.07
    ל
    -0.07
     patrones
    -0.07
    POSITIVE LOGITS
    509
    0.09
    512
    0.08
    Ung
    0.07
     bearing
    0.07
     мең
    0.07
     Mong
    0.07
    511
    0.07
     pouvait
    0.07
    �
    0.07
     fermé
    0.07
    Activations Density 0.003%

    No Known Activations