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. 12722
    Prev
    Next
    INDEX
    Explanations

    board

    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
    ו
    -0.08
     outlining
    -0.08
    融
    -0.08
     walkthrough
    -0.07
    ratio
    -0.07
     bedside
    -0.07
     dozen
    -0.07
    uniform
    -0.07
     Rog
    -0.07
     Wein
    -0.07
    POSITIVE LOGITS
    acher
    0.08
     měla
    0.08
     JLabel
    0.07
     devriez
    0.07
     cạnh
    0.07
    (Label
    0.07
     sufr
    0.07
     práce
    0.07
     UIL
    0.07
     ê
    0.07
    Activations Density 0.001%

    No Known Activations