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. 9204
    Prev
    Next
    INDEX
    Explanations

    contrast

    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
     incurs
    -0.08
     eagerly
    -0.07
    culus
    -0.07
    _INC
    -0.07
     Ain
    -0.07
    _NOTIFY
    -0.07
     sab
    -0.07
    lsen
    -0.07
    _RDONLY
    -0.07
     Gossip
    -0.07
    POSITIVE LOGITS
    Enough
    0.10
     ডিজ
    0.09
    .colors
    0.09
     redesigned
    0.08
     màu
    0.08
     مناسب
    0.08
     체크
    0.08
     garantindo
    0.08
     preto
    0.08
    chart
    0.08
    Activations Density 0.002%

    No Known Activations