© 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. 108622
    Prev
    Next
    INDEX
    Explanations

    math definitions

    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
    구
    -0.08
    OB
    -0.08
    模式
    -0.08
     rekord
    -0.08
    原因
    -0.07
     erklärt
    -0.07
    .rev
    -0.07
    _ir
    -0.07
     구
    -0.07
    !.
    -0.07
    POSITIVE LOGITS
     refers
    0.14
     referring
    0.12
     referred
    0.10
     refiere
    0.09
     refer
    0.09
     rifer
    0.08
     sphere
    0.08
     яка
    0.08
    gangspunkt
    0.08
     якім
    0.08
    Activations Density 0.181%

    No Known Activations