© 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. 75520
    Prev
    Next
    INDEX
    Explanations

    bridges

    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
     nyl
    -0.08
     crossroads
    -0.08
    ègre
    -0.08
     pulley
    -0.07
     hallway
    -0.07
     dispute
    -0.07
    ATED
    -0.07
    '>
    -0.07
    ;'>
    -0.07
     upgraded
    -0.07
    POSITIVE LOGITS
    онач
    0.10
     dames
    0.10
     заявки
    0.08
    ฝ่าย
    0.08
     fase
    0.08
     Lizenz
    0.08
     Bereits
    0.08
     fases
    0.08
     चरण
    0.07
     principale
    0.07
    Activations Density 0.005%

    No Known Activations