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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 5829
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     creme
    -0.08
     Agência
    -0.08
    umva
    -0.08
     الفيلم
    -0.08
     hük
    -0.08
    itudes
    -0.08
     société
    -0.08
    önnum
    -0.08
    Université
    -0.08
    大众
    -0.08
    POSITIVE LOGITS
     division
    0.17
     playoffs
    0.17
     división
    0.16
     playoff
    0.16
     divis
    0.16
     Division
    0.15
     Eastern
    0.15
     postseason
    0.15
     Play
    0.14
    division
    0.14
    Activations Density 0.029%

    No Known Activations