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. 112616
    Prev
    Next
    INDEX
    Explanations

    io

    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
    Central
    -0.08
     орт
    -0.08
    Baseline
    -0.08
    Boundary
    -0.08
    .Dir
    -0.08
    _boundary
    -0.07
    baseline
    -0.07
     Dir
    -0.07
     boundary
    -0.07
    _File
    -0.07
    POSITIVE LOGITS
     Investors
    0.09
    sterdam
    0.08
    zna
    0.08
     planeta
    0.08
     Trader
    0.08
     Richard
    0.07
    umn
    0.07
     naturelles
    0.07
     자연
    0.07
     tumors
    0.07
    Activations Density 0.005%

    No Known Activations