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. 130071
    Prev
    Next
    INDEX
    Explanations

    personal communication/citations

    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
     zašt
    -0.08
     ochron
    -0.08
     mistakenly
    -0.08
     wrong
    -0.08
     wszystkim
    -0.08
     profiles
    -0.08
     DR
    -0.08
    -0.08
     manga
    -0.08
     stealing
    -0.07
    POSITIVE LOGITS
     fertile
    0.09
    оглас
    0.09
    	manager
    0.08
    Courier
    0.08
    097
    0.08
    olus
    0.08
    ในการ
    0.07
    联系人
    0.07
    	admin
    0.07
    คน
    0.07
    Activations Density 0.002%

    No Known Activations