© 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. 45279
    Prev
    Next
    INDEX
    Explanations

    repetition

    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
     vaut
    -0.08
    农村
    -0.08
    anghai
    -0.08
     fiscalização
    -0.07
     וועג
    -0.07
    	Public
    -0.07
    (evt
    -0.07
    .Receive
    -0.07
    екции
    -0.07
     functionalities
    -0.07
    POSITIVE LOGITS
     لتحقيق
    0.08
     tendon
    0.08
     varied
    0.08
     prolonged
    0.08
     tener
    0.08
     đủ
    0.08
     трениров
    0.08
     eignet
    0.08
    казывать
    0.07
     genügend
    0.07
    Activations Density 0.007%

    No Known Activations