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. 30014
    Prev
    Next
    INDEX
    Explanations

    player

    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
    stage
    -0.08
    version
    -0.07
    ero
    -0.07
     impairment
    -0.07
     involving
    -0.07
    cmd
    -0.07
     stadium
    -0.07
    _cmd
    -0.07
    pathname
    -0.07
    idata
    -0.07
    POSITIVE LOGITS
    에게
    0.09
     मिल
    0.09
    觉得
    0.09
     else's
    0.09
    们
    0.09
     froh
    0.08
     Fond
    0.08
     توافق
    0.08
     satisfait
    0.08
     tərəfindən
    0.08
    Activations Density 0.008%

    No Known Activations