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. 77519
    Prev
    Next
    INDEX
    Explanations

    the

    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
     NST
    -0.07
     zwięks
    -0.07
     DVB
    -0.07
    _peng
    -0.07
    .constructor
    -0.07
    -0.07
    โด
    -0.07
     sprintf
    -0.07
     nargin
    -0.07
    完善
    -0.07
    POSITIVE LOGITS
     Tarot
    0.10
     ખે
    0.10
     tarot
    0.10
     ไพ่
    0.10
     kaarten
    0.09
     rollen
    0.09
     карты
    0.09
     질문
    0.09
    entscheidung
    0.09
     beteken
    0.09
    Activations Density 0.013%

    No Known Activations