© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 69767
    Prev
    Next
    INDEX
    Explanations

    chatbot prompt

    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
     MHz
    -0.08
    .flink
    -0.08
     подключения
    -0.08
    .azure
    -0.08
     Tensor
    -0.08
    avaju
    -0.07
    Tensor
    -0.07
     amus
    -0.07
     Feria
    -0.07
    Mux
    -0.07
    POSITIVE LOGITS
     nations
    0.09
     nation
    0.09
     recommendations
    0.09
     sacrifice
    0.08
     Recommendations
    0.08
     persuasion
    0.08
     maximize
    0.08
     violent
    0.08
    Recommendations
    0.08
     killings
    0.08
    Activations Density 0.002%

    No Known Activations