© 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. 23-RESID-POST-AA
    11. 6182
    Prev
    Next
    INDEX
    Explanations

    repetition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     patrim
    -0.08
     perifer
    -0.07
     perif
    -0.07
    无遮
    -0.07
     전망
    -0.06
    ិ
    -0.06
     nort
    -0.06
     seren
    -0.06
    utung
    -0.06
     secluded
    -0.06
    POSITIVE LOGITS
    重复
    0.59
     repeats
    0.56
     repetition
    0.55
     repeated
    0.54
     duplicates
    0.54
     repetitions
    0.52
     duplicate
    0.52
     duplicated
    0.51
     repeating
    0.50
     duplication
    0.50
    Activations Density 0.469%

    No Known Activations