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. 43709
    Prev
    Next
    INDEX
    Explanations

    dp

    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
    rega
    -0.08
    utum
    -0.08
    文化
    -0.08
    .Environment
    -0.08
     stade
    -0.08
    ités
    -0.08
    scribers
    -0.08
    àn
    -0.07
     rhythm
    -0.07
    	camera
    -0.07
    POSITIVE LOGITS
     승인
    0.09
     Bhag
    0.09
     الهدف
    0.08
     നേ
    0.08
    콩
    0.08
     RP
    0.08
     portug
    0.08
     Brazilian
    0.08
     жі
    0.08
     PAC
    0.08
    Activations Density 0.002%

    No Known Activations