© 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. 3-RESID-POST-AA
    11. 12915
    Prev
    Next
    INDEX
    Explanations

    重

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aṣ
    -0.08
     बात
    -0.07
    cohol
    -0.07
     cryptocurrency
    -0.07
     اق
    -0.07
     champ
    -0.07
     Polaris
    -0.07
     Email
    -0.07
    รายการ
    -0.07
     cena
    -0.07
    POSITIVE LOGITS
    stände
    0.08
    -training
    0.08
     straps
    0.08
     ligament
    0.07
    不知道
    0.07
     BEEN
    0.07
     تدري
    0.07
    0.07
    	panic
    0.07
    ificates
    0.07
    Activations Density 0.002%
    No Known Activations