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. 15-RESID-POST-AA
    6. 18996
    Prev
    Next
    INDEX
    Explanations

    Say "-"

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acabado
    -0.08
     sombr
    -0.08
    weza
    -0.08
    ipper
    -0.08
    IMA
    -0.08
     agrade
    -0.08
    abora
    -0.08
     kinky
    -0.08
    രോ
    -0.07
    শেষ
    -0.07
    POSITIVE LOGITS
     teraz
    0.08
     विल
    0.08
     now
    0.07
     ```↵
    0.07
     linh
    0.07
                          
    0.07
     avec
    0.07
    ونی
    0.07
     famil
    0.07
    	validate
    0.07
    Activations Density 0.005%

    No Known Activations