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. 43112
    Prev
    Next
    INDEX
    Explanations

    a

    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
     blades
    -0.09
    综合在线
    -0.08
    انهن
    -0.08
     alber
    -0.08
     enclave
    -0.08
    彻
    -0.08
     consolidated
    -0.07
     aloj
    -0.07
    ਨਾ
    -0.07
     housing
    -0.07
    POSITIVE LOGITS
     あ
    0.08
     เทคนิค
    0.08
     ขั้น
    0.08
    idents
    0.08
    乗
    0.08
     مرحله
    0.07
     เด
    0.07
     النظام
    0.07
    �
    0.07
     بناء
    0.07
    Activations Density 0.000%

    No Known Activations