© 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. 91287
    Prev
    Next
    INDEX
    Explanations

    off-season travel

    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
     destiny
    -0.08
    ตี
    -0.07
     caminos
    -0.07
    τοποι
    -0.07
     complementary
    -0.07
     कर
    -0.07
    browse
    -0.07
    path
    -0.07
     desaparecer
    -0.07
     backs
    -0.07
    POSITIVE LOGITS
     کمتر
    0.10
     зимой
    0.09
     није
    0.09
     Baltimore
    0.09
     সালে
    0.08
    January
    0.08
     կողմ
    0.08
    اولة
    0.08
    ikko
    0.08
    Amsterdam
    0.08
    Activations Density 0.009%

    No Known Activations