© 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. 30106
    Prev
    Next
    INDEX
    Explanations

    eraser

    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
    盛
    -0.09
    woo
    -0.08
    _static
    -0.08
    �
    -0.07
    囲
    -0.07
    -David
    -0.07
    mast
    -0.07
     rogue
    -0.07
     Xen
    -0.07
     hem
    -0.07
    POSITIVE LOGITS
    掉
    0.08
    odings
    0.08
     всё
    0.08
     comprim
    0.07
     слова
    0.07
     మాట
    0.07
    म्म
    0.07
    始
    0.07
     quadratic
    0.07
     সব
    0.07
    Activations Density 0.005%

    No Known Activations