© 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 EvalsExportsinterp-engineNEWAPI 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. 63319
    Prev
    Next
    INDEX
    Explanations

    math proofs

    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
     escon
    -0.08
     Cork
    -0.08
     Hybrid
    -0.08
    包括
    -0.08
     scare
    -0.08
    bour
    -0.08
     फुट
    -0.08
    ರಿ
    -0.08
     historic
    -0.08
    限定
    -0.07
    POSITIVE LOGITS
    Thus
    0.09
     expresses
    0.08
     expressed
    0.08
     выраж
    0.08
    따
    0.08
     telesc
    0.07
     express
    0.07
    Hmm
    0.07
     proport
    0.07
     Ле
    0.07
    Activations Density 0.149%

    No Known Activations