© 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. 26577
    Prev
    Next
    INDEX
    Explanations

    Calculation problems

    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
     those
    -0.08
     covered
    -0.08
    orto
    -0.07
    λίου
    -0.07
     infin
    -0.07
    传媒
    -0.07
     piyas
    -0.07
    ابل
    -0.07
     Sally
    -0.07
     alarma
    -0.07
    POSITIVE LOGITS
     Aim
    0.08
    进去
    0.08
     إليها
    0.08
    Assigned
    0.08
     vetted
    0.08
     Assigned
    0.08
     aliqu
    0.08
     туда
    0.08
     ideological
    0.07
     exclusively
    0.07
    Activations Density 0.036%

    No Known Activations