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. 90273
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     Ii
    -0.09
    ார
    -0.08
     eligibility
    -0.08
    -0.07
    äll
    -0.07
     mikä
    -0.07
     BUG
    -0.07
     Tages
    -0.07
    _feedback
    -0.07
     withdrawn
    -0.07
    POSITIVE LOGITS
     atención
    0.10
    -plus
    0.09
     सम्म
    0.09
     మంది
    0.08
     aten
    0.08
    Attention
    0.08
    DNS
    0.08
    份
    0.08
    oty
    0.08
     подряд
    0.08
    Activations Density 0.044%

    No Known Activations