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. 65252
    Prev
    Next
    INDEX
    Explanations

    Returns

    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
     pany
    -0.09
     honeymoon
    -0.09
     positivity
    -0.08
    .hostname
    -0.08
     SALES
    -0.08
     assim
    -0.08
     ടീമ
    -0.08
     Amal
    -0.08
     teamwork
    -0.08
     empath
    -0.08
    POSITIVE LOGITS
     Republicans
    0.08
    lec
    0.07
    Jag
    0.07
    (Graphics
    0.07
     граф
    0.07
     Presidential
    0.07
    crete
    0.07
    ूर
    0.07
    volved
    0.07
    égi
    0.07
    Activations Density 0.002%

    No Known Activations