© 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. 11-RESID-POST-AA
    11. 47192
    Prev
    Next
    INDEX
    Explanations

    )

    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
    的发展
    -0.08
     vuil
    -0.08
     Ident
    -0.08
    aries
    -0.08
     акту
    -0.07
     oss
    -0.07
     voks
    -0.07
    ட்டு
    -0.07
    ட்டை
    -0.07
    Identify
    -0.07
    POSITIVE LOGITS
     తెలిప
    0.08
     sinabi
    0.08
     ilan
    0.08
     જણાવ્યું
    0.08
     говорится
    0.08
    0.08
     പറഞ്ഞു
    0.07
     îl
    0.07
     कहते
    0.07
     કહે
    0.07
    Activations Density 0.004%
    No Known Activations