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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64081
    Prev
    Next
    INDEX
    Explanations

    Fingers and closing nostrils

    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
     thick
    -0.08
     conver
    -0.07
    Universal
    -0.07
     universit
    -0.07
    互联网
    -0.06
    lya
    -0.06
    Cons
    -0.06
    Conditional
    -0.06
     uniform
    -0.06
    Illustr
    -0.06
    POSITIVE LOGITS
    _removed
    0.10
     remport
    0.10
    	swap
    0.09
     Removed
    0.09
     Goddess
    0.09
     protested
    0.09
    swap
    0.09
     donkey
    0.08
     deity
    0.08
    agę
    0.08
    Activations Density 0.000%

    No Known Activations