Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2478
    Prev
    Next
    INDEX
    Explanations

    The Machine Stops

    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
    �
    -0.08
     Assault
    -0.08
     Hol
    -0.07
    Armor
    -0.07
     Queens
    -0.07
    Resp
    -0.07
    Вес
    -0.07
    dep
    -0.07
    �
    -0.07
    Protected
    -0.07
    POSITIVE LOGITS
     paradox
    0.09
     ज
    0.08
     Antoine
    0.08
    -Sch
    0.08
     Jim
    0.07
     الل
    0.07
     الذ
    0.07
     यूर
    0.07
     wegen
    0.07
    试看
    0.07
    Activations Density 7.024%

    No Known Activations