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. 49349
    Prev
    Next
    INDEX
    Explanations

    energy

    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
     opere
    -0.08
     colo
    -0.08
    本金
    -0.08
     quals
    -0.08
     Scratch
    -0.08
    裂
    -0.08
    .thrift
    -0.08
     sieht
    -0.07
     Evan
    -0.07
     Ellis
    -0.07
    POSITIVE LOGITS
     উন্ন
    0.09
    enh
    0.09
    imized
    0.09
    elligent
    0.08
    adaptive
    0.08
     amélior
    0.08
    -efficient
    0.08
    -aware
    0.08
    -minded
    0.08
     تحسين
    0.07
    Activations Density 0.010%

    No Known Activations