© 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. 2508
    Prev
    Next
    INDEX
    Explanations

    自己

    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
     Oft
    -0.08
     Jad
    -0.08
    �
    -0.08
     Jerome
    -0.08
     الشيخ
    -0.07
     unga
    -0.07
     beein
    -0.07
     Mme
    -0.07
     pek
    -0.07
    ئە
    -0.07
    POSITIVE LOGITS
     depth
    0.08
    aped
    0.08
     sine
    0.08
     reflux
    0.08
     motive
    0.08
    Compart
    0.07
     trie
    0.07
    maal
    0.07
     WH
    0.07
     tramp
    0.07
    Activations Density 0.000%

    No Known Activations