© 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. 44811
    Prev
    Next
    INDEX
    Explanations

    should

    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
     নিজেদের
    -0.09
    адки
    -0.08
     সবাই
    -0.07
     অস
    -0.07
    一起
    -0.07
    ーション
    -0.07
     reput
    -0.07
     wollten
    -0.07
    �
    -0.07
     əmək
    -0.07
    POSITIVE LOGITS
     myself
    0.10
    ’m
    0.10
     છું
    0.09
     हूँ
    0.09
     suis
    0.08
     हूं
    0.08
    ifa
    0.08
     mich
    0.08
     am
    0.08
     personally
    0.08
    Activations Density 0.056%

    No Known Activations