© 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. 47324
    Prev
    Next
    INDEX
    Explanations

    to

    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
     fazemos
    -0.08
     fana
    -0.08
     fórmula
    -0.08
    .glob
    -0.08
     stendur
    -0.08
    .Parameters
    -0.08
     ukub
    -0.08
     કર્મ
    -0.08
     Trademark
    -0.08
     steht
    -0.08
    POSITIVE LOGITS
     부탁
    0.13
    お願いします
    0.11
    お願い
    0.11
     urgently
    0.11
    お願
    0.10
     asap
    0.10
    해주세요
    0.09
    주세요
    0.09
     ASAP
    0.09
     urgent
    0.09
    Activations Density 0.165%

    No Known Activations