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. 43205
    Prev
    Next
    INDEX
    Explanations

    code

    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
     прип
    -0.08
    Doors
    -0.08
    ਸ
    -0.08
     Earrings
    -0.08
    સ્મ
    -0.08
    ząd
    -0.07
    quip
    -0.07
     Radi
    -0.07
     Cups
    -0.07
    편
    -0.07
    POSITIVE LOGITS
    {}'.
    0.09
    ︎
    0.09
     fi
    0.09
    xxxx
    0.09
    115
    0.09
    143
    0.08
    _____
    0.08
    .GUI
    0.08
    30
    0.08
     {}'.
    0.08
    Activations Density 0.039%

    No Known Activations