© 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. 45262
    Prev
    Next
    INDEX
    Explanations

    Paper weights/measurements

    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
     Exp
    -0.08
    windows
    -0.08
     palindrome
    -0.07
     выполнить
    -0.07
    -0.07
    idor
    -0.07
    Dex
    -0.07
     친
    -0.07
    ichael
    -0.07
    etheus
    -0.07
    POSITIVE LOGITS
    厚
    0.10
     แกรม
    0.10
    ីឡ
    0.09
     cardstock
    0.09
    മുള്ള
    0.09
    მწ
    0.09
    Density
    0.08
    ҷа
    0.08
    สปีด
    0.08
    مطحنة
    0.08
    Activations Density 0.007%
    No Known Activations