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. 61005
    Prev
    Next
    INDEX
    Explanations

    pressure

    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
    .public
    -0.08
     nuts
    -0.07
     expert
    -0.07
    .end
    -0.07
     stakeholders
    -0.07
    という
    -0.07
    专家
    -0.07
    .for
    -0.07
    年度
    -0.07
     Expert
    -0.07
    POSITIVE LOGITS
     entsteht
    0.10
    Apartamento
    0.09
     venezol
    0.09
    -negative
    0.09
     huset
    0.09
     hollow
    0.09
     Boh
    0.09
     बनाउन
    0.09
     motel
    0.08
    UAL
    0.08
    Activations Density 0.004%

    No Known Activations