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. 103404
    Prev
    Next
    INDEX
    Explanations

    linguistics

    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
    ਿਕ
    -0.08
     ਜੋ
    -0.08
     ciclos
    -0.07
    ify
    -0.07
    իզ
    -0.07
    ിപ്പ്
    -0.07
     פעולה
    -0.07
    ize
    -0.07
    小
    -0.07
    符合
    -0.07
    POSITIVE LOGITS
     Fern
    0.08
    ેલું
    0.08
     ગય
    0.08
     przez
    0.08
     ital
    0.08
     हुए
    0.08
    wald
    0.08
     توسط
    0.08
    0.08
    .deleted
    0.07
    Activations Density 0.034%

    No Known Activations