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. 44479
    Prev
    Next
    INDEX
    Explanations

    hair

    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
     bomber
    -0.08
     Exped
    -0.08
    /default
    -0.08
     Eure
    -0.07
    asty
    -0.07
    鹰
    -0.07
     uchar
    -0.07
     Circuit
    -0.07
    વાર
    -0.07
     EIN
    -0.07
    POSITIVE LOGITS
     otorg
    0.08
     bottom
    0.08
    .Weight
    0.08
    Prest
    0.07
    Clipboard
    0.07
    Gravity
    0.07
    יווי
    0.07
    Gain
    0.07
     swimmers
    0.07
     heights
    0.07
    Activations Density 0.001%

    No Known Activations