© 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. 23-RESID-POST-AA
    11. 5919
    Prev
    Next
    INDEX
    Explanations

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lookup
    -0.08
     Rich
    -0.08
     prer
    -0.08
     process
    -0.07
     sest
    -0.07
    ലെ
    -0.07
    Cookie
    -0.07
    PRE
    -0.07
     tempfile
    -0.07
    -0.07
    POSITIVE LOGITS
     โน
    0.09
     Sermitsiaq
    0.09
    020
    0.09
    bbs
    0.08
    022
    0.08
     แมน
    0.08
     ทางเข้า
    0.08
     grip
    0.08
     Ու
    0.08
    	link
    0.08
    Activations Density 0.000%
    No Known Activations