Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90071
    Prev
    Next
    INDEX
    Explanations

    complex numbers

    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
    /light
    -0.09
    错
    -0.08
    ग्र
    -0.07
    그래
    -0.07
    PLAN
    -0.07
     tiny
    -0.07
     relied
    -0.07
     mic
    -0.07
     statements
    -0.07
     hinges
    -0.07
    POSITIVE LOGITS
     Receiving
    0.08
     lawsuit
    0.08
     }}">
    0.08
    )">
    0.08
     lurking
    0.07
     citt
    0.07
     horoscope
    0.07
     Ин
    0.07
     தொ
    0.07
     тази
    0.07
    Activations Density 0.027%

    No Known Activations