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. 58676
    Prev
    Next
    INDEX
    Explanations

    bits

    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
    Sold
    -0.08
    ohy
    -0.08
     jig
    -0.08
    �
    -0.08
     Sheridan
    -0.08
    aan
    -0.08
    Verbose
    -0.08
    _notice
    -0.08
    gä
    -0.08
    Johnny
    -0.07
    POSITIVE LOGITS
     க
    0.08
     dengue
    0.08
     transfers
    0.08
     వీ
    0.08
    ρια
    0.08
     transfer
    0.07
     parms
    0.07
     η
    0.07
     θεω
    0.07
     permitirá
    0.07
    Activations Density 0.003%

    No Known Activations