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. 58393
    Prev
    Next
    INDEX
    Explanations

    20

    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
     obesity
    -0.09
    )--
    -0.08
    .ful
    -0.08
     educação
    -0.08
     قراءة
    -0.08
     empower
    -0.08
     принято
    -0.08
    	Connection
    -0.07
     gatherings
    -0.07
     Xan
    -0.07
    POSITIVE LOGITS
    క
    0.08
     c
    0.07
     butterknife
    0.07
     рем
    0.07
     inser
    0.07
     CGPoint
    0.07
    ину
    0.07
    ాస
    0.07
     dst
    0.07
     sabe
    0.07
    Activations Density 0.001%

    No Known Activations