Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112806
    Prev
    Next
    INDEX
    Explanations

    Pauli exclusion principle

    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
     isp
    -0.08
     primal
    -0.08
     belt
    -0.08
     bow
    -0.08
    nage
    -0.07
     dem
    -0.07
    -0.07
     zurück
    -0.07
    进行了
    -0.07
     wor
    -0.07
    POSITIVE LOGITS
    =function
    0.08
    heli
    0.08
    pant
    0.07
    Uno
    0.07
     போட்ட
    0.07
     செல்ல
    0.07
    (defun
    0.07
     Tidak
    0.07
     تض
    0.07
     Contr
    0.07
    Activations Density 0.002%

    No Known Activations