© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50400
    Prev
    Next
    INDEX
    Explanations

    noise

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     approving
    -0.09
     heshi
    -0.09
     approval
    -0.09
     passports
    -0.09
    -approved
    -0.09
    approval
    -0.09
    approved
    -0.09
     предусматри
    -0.09
    Approval
    -0.09
     sanctioned
    -0.09
    POSITIVE LOGITS
     noise
    0.43
    _noise
    0.38
    Noise
    0.38
     Noise
    0.37
    noise
    0.37
     ruido
    0.35
     noises
    0.32
     шум
    0.31
    �
    0.29
     noisy
    0.28
    Activations Density 0.059%

    No Known Activations