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. 119910
    Prev
    Next
    INDEX
    Explanations

    diagnostic

    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
     tenor
    -0.09
    album
    -0.08
    alm
    -0.07
     perpetr
    -0.07
     thesis
    -0.07
     prevents
    -0.07
     essence
    -0.07
     exorbit
    -0.07
     Thompson
    -0.07
    hero
    -0.07
    POSITIVE LOGITS
    接口
    0.09
    /debug
    0.08
    一下
    0.08
     diagnostic
    0.08
    .Trace
    0.07
     Da
    0.07
     Diagnostics
    0.07
     Displays
    0.07
     kemampuan
    0.07
     Streams
    0.07
    Activations Density 0.002%

    No Known Activations