© 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. 7-RESID-POST-AA
    11. 1224
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.08
    夹
    -0.08
    арб
    -0.07
    flamm
    -0.07
    们
    -0.07
     grim
    -0.07
    ondro
    -0.07
    可信
    -0.07
    boek
    -0.07
    Unter
    -0.07
    POSITIVE LOGITS
     hinweg
    0.08
     echter
    0.08
     ना
    0.08
     DL
    0.08
    ീര
    0.08
     സംഗ
    0.08
     Eindruck
    0.07
    請
    0.07
     Valentine's
    0.07
     ಬಾರಿ
    0.07
    Activations Density 0.005%

    No Known Activations