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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54762
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     gdy
    -0.08
    ാഗത
    -0.08
    층
    -0.07
    െയ
    -0.07
    listener
    -0.07
     strata
    -0.07
     Nazi
    -0.07
     contributions
    -0.07
     propor
    -0.07
    _delegate
    -0.07
    POSITIVE LOGITS
    用于
    0.09
     stocked
    0.09
     consum
    0.08
     versatile
    0.08
     יר
    0.08
    ரம்
    0.08
    ерм
    0.08
     replenish
    0.08
     assorted
    0.08
     recurring
    0.08
    Activations Density 0.020%

    No Known Activations