© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95174
    Prev
    Next
    INDEX
    Explanations

    Covering/discussing

    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
     repl
    -0.08
     chez
    -0.08
     клав
    -0.08
    Caps
    -0.08
    _caps
    -0.08
    Sticker
    -0.08
     cheers
    -0.07
    umbersome
    -0.07
     sloppy
    -0.07
    dm
    -0.07
    POSITIVE LOGITS
     discusses
    0.11
     topics
    0.11
     researched
    0.10
     discussing
    0.10
    深入
    0.10
    涵
    0.10
     আলোচনা
    0.10
    专题
    0.10
    观点
    0.10
    �
    0.10
    Activations Density 0.095%

    No Known Activations