© 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. 24720
    Prev
    Next
    INDEX
    Explanations

    order and precedence

    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
     occasional
    -0.10
    Smooth
    -0.09
     smooth
    -0.08
     poursuivre
    -0.08
     occasionally
    -0.08
    abilirsiniz
    -0.08
    zwe
    -0.08
    inx
    -0.08
     mittels
    -0.07
     Miriam
    -0.07
    POSITIVE LOGITS
     precedence
    0.11
     prioritize
    0.10
     prioritized
    0.10
     Priority
    0.09
     priorit
    0.09
    (priority
    0.09
     Importance
    0.09
     hierarchy
    0.09
    Priority
    0.08
     PRIOR
    0.08
    Activations Density 0.008%

    No Known Activations