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. 98991
    Prev
    Next
    INDEX
    Explanations

    Mars Sample Return

    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
     thesis
    -0.08
     цел
    -0.08
     kust
    -0.08
     잠
    -0.08
     Sociales
    -0.08
     가능
    -0.08
     вполне
    -0.08
    �
    -0.08
     предназнач
    -0.08
     промышлен
    -0.07
    POSITIVE LOGITS
    grade
    0.09
    逸
    0.08
    category
    0.08
     وات
    0.07
    sof
    0.07
     beat
    0.07
    lüğ
    0.07
     generations
    0.07
     grade
    0.07
     immed
    0.07
    Activations Density 0.000%

    No Known Activations