Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54236
    Prev
    Next
    INDEX
    Explanations

    Questions and answers

    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
    Fw
    -0.08
     promete
    -0.08
     маңызды
    -0.08
     abandonar
    -0.07
     dangling
    -0.07
     아닌
    -0.07
     fret
    -0.07
     wish
    -0.07
     तथा
    -0.07
    gmt
    -0.07
    POSITIVE LOGITS
    ครับ
    0.10
     yes
    0.10
     effectivement
    0.10
    ค่ะ
    0.10
     Yes
    0.08
     yeah
    0.08
    Yes
    0.08
     ça
    0.08
    嗯
    0.08
    Depends
    0.08
    Activations Density 0.227%

    No Known Activations