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. 55723
    Prev
    Next
    INDEX
    Explanations

    mannerism

    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
     admitted
    -0.08
     Retriever
    -0.08
    روض
    -0.08
     Jaz
    -0.08
     TD
    -0.08
    aptors
    -0.08
     Md
    -0.08
     lod
    -0.08
    seek
    -0.08
     FT
    -0.08
    POSITIVE LOGITS
    uny
    0.07
     кел
    0.07
     п
    0.07
    Firewall
    0.07
    Configuration
    0.07
     коф
    0.07
     moat
    0.07
    Co
    0.07
    internal
    0.07
     firewall
    0.07
    Activations Density 0.000%

    No Known Activations