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. 102560
    Prev
    Next
    INDEX
    Explanations

    instructions, prompts, requests

    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
     of
    -0.08
     decking
    -0.08
     a
    -0.08
     pave
    -0.08
     pivotal
    -0.07
     implications
    -0.07
     dependent
    -0.07
     picturesque
    -0.07
     поверх
    -0.07
     common
    -0.07
    POSITIVE LOGITS
     출력
    0.12
     输出
    0.11
    输出
    0.11
     Output
    0.11
     OUTPUT
    0.11
     STRICT
    0.11
     আমাকে
    0.10
    回复
    0.10
     ONLY
    0.10
     উত্তর
    0.10
    Activations Density 0.274%

    No Known Activations