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. 44240
    Prev
    Next
    INDEX
    Explanations

    tweak

    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
    gne
    -0.09
     además
    -0.09
     Respond
    -0.08
    ţe
    -0.08
    -0.07
    ляется
    -0.07
     awaken
    -0.07
     Pe
    -0.07
     Problems
    -0.07
    Respond
    -0.07
    POSITIVE LOGITS
     wording
    0.11
     사항
    0.10
     tweaks
    0.09
    please
    0.08
     كي
    0.08
    .modify
    0.08
     ню
    0.08
     please
    0.08
    删
    0.07
     sesuai
    0.07
    Activations Density 0.012%

    No Known Activations