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. 65078
    Prev
    Next
    INDEX
    Explanations

    aff

    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
    xd
    -0.08
    খন
    -0.08
    orp
    -0.08
    ouch
    -0.07
     গভ
    -0.07
     вп
    -0.07
     benchmarks
    -0.07
     keen
    -0.07
     diện
    -0.07
     dubbed
    -0.07
    POSITIVE LOGITS
     scaff
    0.08
    -assisted
    0.08
    ல
    0.08
    梁
    0.08
    perate
    0.07
    Provided
    0.07
     intellectually
    0.07
    ască
    0.07
    provided
    0.07
     lifes
    0.07
    Activations Density 0.001%

    No Known Activations