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. 87963
    Prev
    Next
    INDEX
    Explanations

    CNN layers

    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
    luni
    -0.09
    Cancel
    -0.08
    _cpp
    -0.08
    cancel
    -0.08
    ===↵
    -0.08
    DDS
    -0.08
     Kirby
    -0.08
    -------------
    -0.08
    Cancelled
    -0.08
    cpp
    -0.08
    POSITIVE LOGITS
     Hö
    0.09
     taboo
    0.08
     slogans
    0.08
    ೇಹ
    0.08
    ಾಬ
    0.08
     styling
    0.08
    ече
    0.08
     rist
    0.08
     chaos
    0.08
     porod
    0.08
    Activations Density 0.001%

    No Known Activations