© 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. 31122
    Prev
    Next
    INDEX
    Explanations

    Commas and the number 1

    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
     Beethoven
    -0.09
     morce
    -0.08
     motifs
    -0.08
     mecan
    -0.08
     murals
    -0.08
     despi
    -0.08
     bitmap
    -0.08
    {EIF
    -0.08
     Casper
    -0.08
     consoles
    -0.08
    POSITIVE LOGITS
     dissolve
    0.09
    girl
    0.08
    _parent
    0.08
    ay
    0.08
    Yo
    0.07
     kul
    0.07
     boy
    0.07
    �
    0.07
    Shelf
    0.07
     hike
    0.07
    Activations Density 0.001%

    No Known Activations