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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120360
    Prev
    Next
    INDEX
    Explanations

    mathematics and instructions

    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
     pripr
    -0.08
     Jacques
    -0.07
    Aplic
    -0.07
     melk
    -0.07
    准备
    -0.07
    ademark
    -0.07
    Gram
    -0.07
    _FN
    -0.07
    (param
    -0.07
     представлены
    -0.07
    POSITIVE LOGITS
    솔
    0.08
     någon
    0.08
    ensee
    0.07
    ındaki
    0.07
    ресс
    0.07
    הש
    0.07
    unsafe
    0.07
    েরা
    0.07
    ress
    0.07
     Seoul
    0.07
    Activations Density 0.000%

    No Known Activations