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. 43614
    Prev
    Next
    INDEX
    Explanations

    period

    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
    (org
    -0.08
    Mond
    -0.07
    .Org
    -0.07
     org
    -0.07
    ỡ
    -0.07
    Gee
    -0.07
    zed
    -0.07
    AM
    -0.07
    sect
    -0.07
    University
    -0.07
    POSITIVE LOGITS
     nai
    0.09
     XXXXX
    0.08
    prima
    0.08
    -danger
    0.08
    085
    0.08
     sob
    0.08
     Shell
    0.08
    685
    0.07
     XXXX
    0.07
    Shell
    0.07
    Activations Density 0.035%

    No Known Activations