© 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. 12978
    Prev
    Next
    INDEX
    Explanations

    доступ

    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
     Vid
    -0.08
    International
    -0.07
    є
    -0.07
    Vid
    -0.07
    130
    -0.07
    146
    -0.07
    Ń
    -0.07
    �
    -0.07
    投诉
    -0.07
     pencil
    -0.07
    POSITIVE LOGITS
     ly
    0.08
     abb
    0.08
     Kol
    0.08
     Seren
    0.07
     hangi
    0.07
    �
    0.07
     التن
    0.07
     lay
    0.07
     kronor
    0.07
     Ben
    0.07
    Activations Density 0.002%

    No Known Activations