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. 42116
    Prev
    Next
    INDEX
    Explanations

    masks

    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
    ラ
    -0.09
     terreno
    -0.07
    шир
    -0.07
     gastr
    -0.07
    ındaki
    -0.07
    cells
    -0.07
     numbering
    -0.07
     sequ
    -0.07
    _Date
    -0.07
     unfold
    -0.07
    POSITIVE LOGITS
     universally
    0.11
     режима
    0.09
    举
    0.09
     habits
    0.09
     obligatoire
    0.09
     правила
    0.08
     режим
    0.08
     wereldwijd
    0.08
     Had
    0.08
     профилакти
    0.08
    Activations Density 0.012%

    No Known Activations