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. 45170
    Prev
    Next
    INDEX
    Explanations

    im

    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
     싸
    -0.08
     deciding
    -0.08
    Security
    -0.07
    ন্টার
    -0.07
    Nevertheless
    -0.07
    Bearer
    -0.07
     greater
    -0.07
    বেন
    -0.07
    jó
    -0.07
    ্যাল
    -0.07
    POSITIVE LOGITS
     देखि
    0.09
     gef
    0.09
     trekt
    0.08
     描
    0.08
     മുതൽ
    0.08
     dvije
    0.08
     одного
    0.08
     ഒര
    0.07
     GREEN
    0.07
     tof
    0.07
    Activations Density 0.010%

    No Known Activations