Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 26641
    Prev
    Next
    INDEX
    Explanations

    instant

    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
    �
    -0.09
     произошло
    -0.08
     commiss
    -0.08
    хь
    -0.08
     aca
    -0.08
    ायण
    -0.08
     Ars
    -0.08
     Edith
    -0.08
     Trainings
    -0.08
    CEPTION
    -0.08
    POSITIVE LOGITS
     adventure
    0.08
     znač
    0.08
     independ
    0.08
     foam
    0.08
    main
    0.08
     �
    0.07
     的
    0.07
    word
    0.07
    owy
    0.07
     fail
    0.07
    Activations Density 0.003%

    No Known Activations