© 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. 522
    Prev
    Next
    INDEX
    Explanations

    deposit

    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
     machines
    -0.08
     arriva
    -0.08
     Bisa
    -0.08
     Machines
    -0.07
     SQLITE
    -0.07
     prive
    -0.07
     shoes
    -0.07
     AGRE
    -0.07
     hoteles
    -0.07
     TVs
    -0.07
    POSITIVE LOGITS
    œ
    0.09
    Collected
    0.09
     hoeveelheid
    0.09
    納
    0.09
    وعة
    0.08
     aanb
    0.08
     colet
    0.08
     Fairy
    0.08
     collected
    0.07
     collectie
    0.07
    Activations Density 0.000%

    No Known Activations