Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 78642
    Prev
    Next
    INDEX
    Explanations

    "of"

    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
    blas
    -0.08
    iffe
    -0.08
     warehouses
    -0.08
    oinen
    -0.08
    ious
    -0.08
    게
    -0.08
    简称
    -0.08
     �
    -0.08
    pref
    -0.08
    正常
    -0.07
    POSITIVE LOGITS
    260
    0.07
     aut
    0.07
    Marked
    0.07
    Opcode
    0.07
     Mein
    0.07
     MGA
    0.07
    'A
    0.07
    831
    0.07
     Opcode
    0.07
     Axis
    0.07
    Activations Density 0.007%

    No Known Activations