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. 111584
    Prev
    Next
    INDEX
    Explanations

    sub

    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
     chemically
    -0.09
     south
    -0.09
     southwest
    -0.09
    south
    -0.09
    ='../
    -0.08
     physically
    -0.08
     northwest
    -0.08
    CTL
    -0.08
     />,↵
    -0.07
     north
    -0.07
    POSITIVE LOGITS
     തല
    0.10
    菜
    0.08
    prog
    0.08
     หลัง
    0.08
     수준
    0.07
     lea
    0.07
     바로
    0.07
     supper
    0.07
    _axes
    0.07
    _items
    0.07
    Activations Density 0.006%

    No Known Activations