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. 60558
    Prev
    Next
    INDEX
    Explanations

    beans

    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
    Ignore
    -0.08
     battery
    -0.08
    成人电影
    -0.08
     addictions
    -0.07
     regulation
    -0.07
     mas
    -0.07
    ADI
    -0.07
     simulation
    -0.07
     bater
    -0.07
     articol
    -0.07
    POSITIVE LOGITS
    (repo
    0.08
     hint
    0.08
    _HINT
    0.08
     kaffe
    0.08
     تُ
    0.08
     briefs
    0.08
     victorious
    0.08
     arches
    0.08
     planten
    0.08
     toasted
    0.07
    Activations Density 0.003%

    No Known Activations