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. 9140
    Prev
    Next
    INDEX
    Explanations

    干

    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
     اینکه
    -0.09
    Invocation
    -0.08
    hach
    -0.07
    عراض
    -0.07
     langsam
    -0.07
    format
    -0.07
    这种
    -0.07
    ịa
    -0.07
     monoch
    -0.07
    口コミ
    -0.07
    POSITIVE LOGITS
     advisory
    0.10
     Advisory
    0.09
     advis
    0.09
    екомен
    0.08
     ej
    0.08
    insula
    0.08
    qo
    0.08
     Bag
    0.08
    	errors
    0.08
     Authorities
    0.08
    Activations Density 0.000%

    No Known Activations