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. 52799
    Prev
    Next
    INDEX
    Explanations

    arily

    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
    кового
    -0.08
    ன
    -0.08
     SEM
    -0.07
    .bar
    -0.07
     Lom
    -0.07
    व्हा
    -0.07
    路线
    -0.07
    (bar
    -0.07
    Route
    -0.07
    .Bar
    -0.07
    POSITIVE LOGITS
     increasingly
    0.09
     ente
    0.08
     Build
    0.08
     certa
    0.08
     zen
    0.08
     vse
    0.08
     степень
    0.08
     extent
    0.08
    ashi
    0.08
    Increasing
    0.08
    Activations Density 0.005%

    No Known Activations