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. 43772
    Prev
    Next
    INDEX
    Explanations

    relational databases

    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
    ڈ
    -0.09
     Springs
    -0.08
     assets
    -0.08
    haft
    -0.08
    inecraft
    -0.07
     backgrounds
    -0.07
     energy
    -0.07
     ascertain
    -0.07
     Solidity
    -0.07
     بیشتری
    -0.07
    POSITIVE LOGITS
     Cartesian
    0.09
     imper
    0.09
     Peut
    0.08
     mutil
    0.08
    �
    0.08
    Cartesian
    0.08
    (tbl
    0.08
    uest
    0.08
     encycl
    0.08
     rectangular
    0.08
    Activations Density 0.004%

    No Known Activations