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. 102902
    Prev
    Next
    INDEX
    Explanations

    woman

    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
     specified
    -0.09
     communicating
    -0.08
     предлагаем
    -0.08
    specified
    -0.08
    tingham
    -0.07
     collaborating
    -0.07
    634
    -0.07
     ചെയ്യുന്ന
    -0.07
     depended
    -0.07
    송
    -0.07
    POSITIVE LOGITS
     herv
    0.08
     ketchup
    0.08
    黄色
    0.08
     Helf
    0.08
     Rosen
    0.08
     LP
    0.08
     næste
    0.08
     黄色
    0.07
    .Btn
    0.07
    Lp
    0.07
    Activations Density 0.000%

    No Known Activations