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. 76315
    Prev
    Next
    INDEX
    Explanations

    ::

    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
    Ara
    -0.08
    _reports
    -0.08
     Dun
    -0.08
     apparatus
    -0.08
     upwards
    -0.08
     Ara
    -0.08
     supp
    -0.07
     share
    -0.07
    _threads
    -0.07
     Twe
    -0.07
    POSITIVE LOGITS
    تع
    0.08
     Sikh
    0.08
     shah
    0.08
     નિવ
    0.08
    ели
    0.08
    েশন
    0.08
    =forms
    0.07
    pewa
    0.07
    -black
    0.07
    ICK
    0.07
    Activations Density 0.001%

    No Known Activations