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. 374
    Prev
    Next
    INDEX
    Explanations

    Space law

    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
     고객
    -0.09
     kunder
    -0.08
     Customer
    -0.08
     ग्राहक
    -0.08
    ustomer
    -0.08
     Kunden
    -0.08
    pe
    -0.07
    ોર્ટ
    -0.07
     gauge
    -0.07
    eback
    -0.07
    POSITIVE LOGITS
    公平
    0.10
     justa
    0.10
     treaty
    0.09
    Declare
    0.09
     política
    0.09
     Política
    0.09
     Treaty
    0.08
    LICENSE
    0.08
     equitable
    0.08
     eerlijk
    0.08
    Activations Density 0.008%

    No Known Activations