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. 90088
    Prev
    Next
    INDEX
    Explanations

    v

    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
    bles
    -0.09
    boats
    -0.07
     stuff
    -0.07
    _strip
    -0.07
    остей
    -0.07
    ])(
    -0.07
    以来
    -0.07
    triangle
    -0.07
     monoton
    -0.07
    upported
    -0.07
    POSITIVE LOGITS
     crem
    0.08
    ancée
    0.08
     Bal
    0.07
     Luo
    0.07
     ebenfalls
    0.07
     रिज
    0.07
     wela
    0.07
    יאל
    0.07
     프로
    0.07
     year's
    0.07
    Activations Density 0.004%

    No Known Activations