© 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. 12940
    Prev
    Next
    INDEX
    Explanations

    ed

    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
    ewise
    -0.08
    ових
    -0.08
    ">',↵
    -0.08
    க்
    -0.08
    �
    -0.08
    ีย
    -0.08
    �
    -0.08
     Wise
    -0.08
     cult
    -0.07
     modest
    -0.07
    POSITIVE LOGITS
    �
    0.09
     dug
    0.08
     Unterkunft
    0.08
    lot
    0.08
     remnants
    0.08
     tup
    0.08
     Rut
    0.08
     исправ
    0.08
     पुराने
    0.08
     вокруг
    0.08
    Activations Density 0.006%

    No Known Activations