© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 75497
    Prev
    Next
    INDEX
    Explanations

    inside

    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
     tip
    -0.08
     laser
    -0.08
    Tip
    -0.08
     curb
    -0.08
    (candidate
    -0.07
    opy
    -0.07
    (shape
    -0.07
    laser
    -0.07
    ücke
    -0.07
    ీక
    -0.07
    POSITIVE LOGITS
     Composite
    0.08
     CType
    0.08
     unnoticed
    0.08
     Iz
    0.07
     QS
    0.07
     neus
    0.07
     الامر
    0.07
     Satz
    0.07
    علق
    0.07
     них
    0.07
    Activations Density 0.006%

    No Known Activations