© 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. 11-RESID-POST-AA
    11. 78391
    Prev
    Next
    INDEX
    Explanations

    ARK

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yum
    -0.09
     Upt
    -0.09
     humid
    -0.08
    hawm
    -0.07
     Argument
    -0.07
    argument
    -0.07
     retail
    -0.07
     yum
    -0.07
     nz
    -0.07
    ought
    -0.07
    POSITIVE LOGITS
     generations
    0.08
     ontwerpen
    0.08
     генера
    0.08
    生成
    0.08
     inscriptions
    0.07
    師
    0.07
    -registration
    0.07
    -generated
    0.07
     generation
    0.07
     welded
    0.07
    Activations Density 0.001%

    No Known Activations