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. 117535
    Prev
    Next
    INDEX
    Explanations

    不能

    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
     ingén
    -0.09
     Game
    -0.07
     Billboard
    -0.07
     génére
    -0.07
    	Game
    -0.07
     GAME
    -0.07
     Candy
    -0.07
     ntx
    -0.07
     MPG
    -0.07
     ly
    -0.07
    POSITIVE LOGITS
     cumplimiento
    0.09
    须
    0.08
     confidentiality
    0.08
     unacceptable
    0.08
     adhere
    0.08
     uphold
    0.08
     unlawful
    0.08
    orde
    0.08
    原创
    0.08
    ad
    0.07
    Activations Density 0.001%

    No Known Activations