© 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. 3-RESID-POST-AA
    11. 12977
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nge
    -0.08
     meditation
    -0.08
     vents
    -0.07
     blessings
    -0.07
    हरे
    -0.07
     Sh
    -0.07
     innovatie
    -0.07
     कै
    -0.07
     accusations
    -0.07
    sworth
    -0.07
    POSITIVE LOGITS
     seuil
    0.09
     trunk
    0.08
     venc
    0.08
     opts
    0.08
     rama
    0.08
    _SO
    0.07
    'at
    0.07
     sayı
    0.07
     MACH
    0.07
    206
    0.07
    Activations Density 0.207%

    No Known Activations