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. 112385
    Prev
    Next
    INDEX
    Explanations

    content

    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
    ør
    -0.08
     Alpine
    -0.08
     exit
    -0.07
    otif
    -0.07
     oblast
    -0.07
    -0.07
    _bar
    -0.07
    极
    -0.07
     halftime
    -0.07
     reactive
    -0.07
    POSITIVE LOGITS
     Commissioners
    0.09
    皇
    0.09
    _URI
    0.08
     dign
    0.08
    DATABASE
    0.08
     Paper
    0.08
    (dataset
    0.08
     DATABASE
    0.08
    icare
    0.08
    Columns
    0.08
    Activations Density 0.002%

    No Known Activations