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. 65682
    Prev
    Next
    INDEX
    Explanations

    →

    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
    _named
    -0.08
    @"
    -0.08
    یه
    -0.08
    فت
    -0.07
     Woods
    -0.07
    важ
    -0.07
    ogram
    -0.07
     conviv
    -0.07
     Waters
    -0.07
    ও
    -0.07
    POSITIVE LOGITS
    趋
    0.12
     tending
    0.10
     approaching
    0.10
     limit
    0.10
     стрем
    0.09
     shrinking
    0.09
    渐
    0.09
     disappe
    0.09
     જતા
    0.09
    趋势
    0.09
    Activations Density 0.015%

    No Known Activations