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. 78513
    Prev
    Next
    INDEX
    Explanations

    ruin

    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
     corps
    -0.10
     Fa
    -0.08
    /google
    -0.07
     சக
    -0.07
    .fa
    -0.07
    님
    -0.07
    RESS
    -0.07
     Corps
    -0.07
     bain
    -0.07
    -sama
    -0.07
    POSITIVE LOGITS
     खराब
    0.08
     miser
    0.08
    不了
    0.08
    掉
    0.08
     sạch
    0.08
     livelihoods
    0.07
     Cy
    0.07
     tư
    0.07
     wrought
    0.07
    enschaften
    0.07
    Activations Density 0.008%

    No Known Activations