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. 12256
    Prev
    Next
    INDEX
    Explanations

    Differential privacy and noise

    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
     représentation
    -0.08
     pregled
    -0.08
    hten
    -0.08
     reaffirm
    -0.07
     skozi
    -0.07
     hi
    -0.07
     représent
    -0.07
    hi
    -0.07
    .Iter
    -0.07
    我们
    -0.07
    POSITIVE LOGITS
     noise
    0.11
     Noise
    0.10
    Noise
    0.10
    _noise
    0.10
     шум
    0.09
    noise
    0.09
    .random
    0.09
     ruido
    0.09
     randomness
    0.08
     generosity
    0.08
    Activations Density 0.000%

    No Known Activations