© 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. 552
    Prev
    Next
    INDEX
    Explanations

    Quantity

    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
     Emulator
    -0.09
     होगा
    -0.08
     består
    -0.08
     performers
    -0.08
     adb
    -0.08
     прошло
    -0.08
     dyr
    -0.08
     डे
    -0.08
     मो
    -0.08
     beve
    -0.08
    POSITIVE LOGITS
     כמ
    0.08
    ectin
    0.08
    .vector
    0.07
    Vec
    0.07
    ());↵
    0.07
    associated
    0.07
    Img
    0.07
     vector
    0.07
    େ
    0.07
    (vector
    0.07
    Activations Density 0.016%

    No Known Activations