Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 129648
    Prev
    Next
    INDEX
    Explanations

    有

    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
     odborn
    -0.07
     facilitating
    -0.07
    toupper
    -0.07
     consequatur
    -0.07
     দর
    -0.07
     lowering
    -0.07
    druk
    -0.07
    aira
    -0.07
     deserving
    -0.07
    వర
    -0.06
    POSITIVE LOGITS
     lifespan
    0.24
    期限
    0.22
     duration
    0.22
    Duration
    0.22
    	duration
    0.21
     durée
    0.20
     Duration
    0.20
     مدة
    0.20
    Expiration
    0.20
    duration
    0.20
    Activations Density 0.094%

    No Known Activations