© 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. 8151
    Prev
    Next
    INDEX
    Explanations

    Stable sorting algorithms

    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
    empl
    -0.08
    一家
    -0.08
    博彩
    -0.08
    entee
    -0.07
     appropri
    -0.07
     Disse
    -0.07
     Steuer
    -0.07
     dissemin
    -0.07
     brethren
    -0.07
     dimensão
    -0.07
    POSITIVE LOGITS
     Preserve
    0.09
     preserve
    0.09
     preserves
    0.09
    稳定
    0.09
     fidèle
    0.09
     stability
    0.09
     maka
    0.09
     Stable
    0.08
    Attack
    0.08
     estabilidad
    0.08
    Activations Density 0.001%

    No Known Activations