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. 77499
    Prev
    Next
    INDEX
    Explanations

    Symmetry

    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
     elektronik
    -0.10
     electrónicos
    -0.09
    電子
    -0.08
     Elektr
    -0.08
     מע
    -0.08
     tani
    -0.08
    扶
    -0.07
     ט
    -0.07
     Coil
    -0.07
     Επι
    -0.07
    POSITIVE LOGITS
     symmetry
    0.13
     Gal
    0.09
    Gal
    0.09
     invari
    0.08
     conserved
    0.08
     spontaneously
    0.08
     vun
    0.08
     gal
    0.08
    Utc
    0.08
     Sacred
    0.08
    Activations Density 0.005%

    No Known Activations